Look for any podcast host, guest or anyone
Showing episodes and shows of

OWASP GenAI Security Project

Shows

The Threat Intelligence Podcast
The Threat Intelligence PodcastWhen AI Models Vote on the Attack | Ep 20One AI model can be rate-limited, blocked, or refuse to cooperate. So what if the attacker uses four? Rachel James and Dr. Bryan Nakayama break down Cisco Talos's research on malware where multiple LLMs vote on the next attack step, acting as a tactical command-and-control panel.Then we turn to Anthropic's analysis of GLM 5.3, an open-weight model that sits only a couple of percentage points behind a safeguards-disabled Mythos Preview on automated exploit development. With the guardrails removed, refusals vanish, and the labs that used to spot misuse can't see what runs on someone else's...
2026-10-1526 minChaos Computer Club - recent audio-only feed
Chaos Computer Club - recent audio-only feedOWASP Cornucopia - Gamifying AI Threat Modeling and Security Requirement Analysis (god2026)Shift-left doesn't start with scanning the code for security vulnerabilities; it begins with designing for security. Too often, the shift-left mantra consists of implementing (AI-powered) code scanning and applying AI-powered security fixes for remediation. Also, don't forget to implement the AI-powered benchmark for AI-powered Security Fixes. Now, to be clear, I am not actually telling you to stop using these tools — if they work for you — instead, we should ask ourselves: What are we working on? What can go wrong? What are we going to do about it? Did we do a good job? In order to support that second ques...
2026-09-2433 minChaos Computer Club - recent events feed (high quality)
Chaos Computer Club - recent events feed (high quality)OWASP Cornucopia - Gamifying AI Threat Modeling and Security Requirement Analysis (god2026)Shift-left doesn't start with scanning the code for security vulnerabilities; it begins with designing for security. Too often, the shift-left mantra consists of implementing (AI-powered) code scanning and applying AI-powered security fixes for remediation. Also, don't forget to implement the AI-powered benchmark for AI-powered Security Fixes. Now, to be clear, I am not actually telling you to stop using these tools — if they work for you — instead, we should ask ourselves: What are we working on? What can go wrong? What are we going to do about it? Did we do a good job? In order to support that second ques...
2026-09-2433 minChaos Computer Club - recent events feed (low quality)
Chaos Computer Club - recent events feed (low quality)OWASP Cornucopia - Gamifying AI Threat Modeling and Security Requirement Analysis (god2026)Shift-left doesn't start with scanning the code for security vulnerabilities; it begins with designing for security. Too often, the shift-left mantra consists of implementing (AI-powered) code scanning and applying AI-powered security fixes for remediation. Also, don't forget to implement the AI-powered benchmark for AI-powered Security Fixes. Now, to be clear, I am not actually telling you to stop using these tools — if they work for you — instead, we should ask ourselves: What are we working on? What can go wrong? What are we going to do about it? Did we do a good job? In order to support that second ques...
2026-09-2433 minChaos Computer Club - recent events feed
Chaos Computer Club - recent events feedOWASP Cornucopia - Gamifying AI Threat Modeling and Security Requirement Analysis (god2026)Shift-left doesn't start with scanning the code for security vulnerabilities; it begins with designing for security. Too often, the shift-left mantra consists of implementing (AI-powered) code scanning and applying AI-powered security fixes for remediation. Also, don't forget to implement the AI-powered benchmark for AI-powered Security Fixes. Now, to be clear, I am not actually telling you to stop using these tools — if they work for you — instead, we should ask ourselves: What are we working on? What can go wrong? What are we going to do about it? Did we do a good job? In order to support that second ques...
2026-09-2433 minResilient Cyber
Resilient CyberThe First OWASP Top 10 Backed by Real Incident DataRock Lambros, Co-Lead of the 2026 OWASP Top 10 for LLM Applications, on why prompt injection would have fallen out of the top 10 based on incident data alone, and why the community kept it at number one anyway.In this episode I sit down with Rock Lambros, longtime security leader, former CISO, core team member of the OWASP GenAI Security Project, and Co-Lead of the 2026 OWASP Top 10 for LLM Applications, to dig into the new list and the harder questions underneath it. We get into the letter from the project leads that opens the document, why the...
2026-09-1425 minAI Radar Italia: News Tech e AI
AI Radar Italia: News Tech e AIG20: l'AI è la nuova elettricità. 100M$ per HiddenLayer e le regole OWASPL'intelligenza artificiale è fondamentale quanto l'acqua e l'elettricità? Jensen Huang e Sam Altman ne sono convinti e lo chiedono al G20.In questo episodio, analizziamo la spinta dei leader tech per rendere l'infrastruttura AI una priorità di sicurezza nazionale. Inoltre: la startup HiddenLayer raccoglie **100 milioni di dollari** per difendere i modelli AI dagli attacchi informatici, e il progetto OWASP pubblica i nuovi standard 2026 per la sicurezza e il controllo degli agenti autonomi.Sources:• TechCrunch: https://techcrunch.com/2026/09/02/hiddenlayer-raises-100m-series-b-as-ai-security-arr-jumps-10x/• Malay Mail: https://www.malaymail.com/news/tech-gadgets/2026/09/03/tech-bosses-press-g20-to-build-ai-data-centres-but-ministers-split-on-risks-and-community-impact-concerns/149866• PR Newswire: https://www.prnewswir...
2026-09-0302 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastWeaponizing Trust: How Nation-States and Criminals Are Hiding Inside the Tools You Already Use | Episode 14Two reports, one uncomfortable theme: attackers aren't doing new things — they're doing old things inside the tools we already trust.Rachel James and Dr. Bryan Nakayama read the fine print with host Dave Hatt.Nation-state actors hiding in plain sight — Trend Micro's six-month look at China, Russia, North Korea, and Iran-aligned groups finds command-and-control living inside Microsoft 365, dev tunnels, and blockchains. One standout: a jailbroken autonomous agent ran a full intrusion loop on its own — scanning, exploitation, credential harvesting, password spraying. Defenders can't just block trusted services, so detection has to move to identity and behavior.Sp...
2026-08-1417 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastAI Just Cracked Post-Quantum Crypto. Is Your Security Team Ready? | Episode 13Two frontier AI labs had autonomous agents attack real-world systems without their knowledge — one incident went undetected for three months. On this episode of the OWASP GenAI Security Project's Threat Intelligence Podcast, hosts Rachel James and Dr. Bryan Nakayama unpack the fallout from the OpenAI/Hugging Face rogue agent incident and Anthropic's own after-the-fact discovery of similar behavior in its eval logs — then turn to the story that should really worry security leaders: an AI model used in red-teaming found a genuine cryptographic flaw in Hawk, a post-quantum signature candidate, fast enough that its own authors withdrew the scheme.
2026-08-0723 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastThe AI Hacker Myth: 3 Days, 6 Minutes, and One Very Buggy Botnet | Episode 12Three headlines, one question: is AI doing something new, or just typing faster?Rachel James and Dr. Brian Nakayama read the fine print with host Dave Hatt.72-hour AWS compromise — Solo actor, no zero-day, no novel malware. The "AI tell" was tempo: four access keys used in the same second, hundreds of parallel SQL queries. Compelling, but nobody has a base rate for what a skilled human does without AI.TuxBot v3 — A vibe-coded botnet that shipped with the model's "for educational purposes only" disclaimer still in it. Broken exploits, hallucinated encryption. Unit 42 rated...
2026-07-3130 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastOpen AI’s Hack of Hugging Face | Episode 11A model was asked to prove how good it was at hacking. It decided the fastest route was to break out of its sandbox and steal the answer sheet.That's the Hugging Face incident in one line. The long version — one poisoned dataset, container escape, lateral movement across Kubernetes clusters, 17,000 attacker actions in a single weekend — is Episode 11.But the detail that should worry security teams isn't the attack. It's the investigation. Hugging Face tried to analyze it with commercial frontier models, hit refusals and cost walls, and ran the forensics on a self-hosted open-weight mode...
2026-07-2431 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastSupply Chain Attacks, Vibe Coding Risks & the Five Eyes AI Warning | Episode 10Hosts Rachel James and Dr. Bryan Nakayama unpack why supply chain attacks are exploding in the age of vibe coding — when AI writes code faster than anyone can security-review it. They walk through recent incidents: the "Cordyceps" CI/CD pipeline flaw affecting Microsoft, Google, Apache and others; the "Miasma" worm that hijacks AI coding assistants at the tool level; and a North Korean actor using a Claude-powered agent to inject a malicious dependency that led to $12M in stolen crypto.Also this episode: the rare joint Five Eyes advisory warning that AI will transform offensive and defensive cy...
2026-07-1626 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastThe First AI-Run Ransomware Attack & How to Tell a Bot Is Attacking You | Episode 9Hosts Rachel James and Dr. Bryan Nakayama break down "Jade Puffer" — what researchers at Sysdig call the first end-to-end agentic ransomware operation, with an LLM driving every step from initial access to cleanup. They explore how forensic investigators proved it was AI (not just a well-resourced human), from self-narrating payloads to error corrections that happen faster than any person could type.Also this episode: an update on Anthropic's Fable and Mythos models coming back online after US export controls, what the government's growing control over model access means for defenders, and why — as always — it's less about the mo...
2026-07-1515 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastInside Anthropic's Threat Report: The AI Risk Enablement Score & the Rise of Orchestration | Episode 8Hosts Rachel James and Dr. Bryan Nakayama dig into Anthropic's June threat report and its first-ever AI Risk Enablement Score (ARES) — built from 832 banned accounts and 14,000 observations, mapped to the MITRE ATT&CK framework. They explore why frontier labs have unique visibility into how threat actors weaponize AI, where the scoring still falls short, and the report's biggest takeaway: it's not about the model, it's about orchestration.Covered this episode: how AI gives uneven "uplift" to script kiddies vs. nation-state APTs, why the most dangerous behavior is the least observable, agentic attack chaining, and how defenders can us...
2026-07-1526 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastAnthropic's Fable & Mythos Shutdown | Episode 7Hosts Rachel James and Dr. Bryan Nakayama unpack a world first: on June 12th the US government had Anthropic pull Fable 5 and Mythos 5 worldwide — not banning a chip or a weapon, but a model itself. They dig into where the line was drawn ("fix this code"), why pulling these models may hurt defenders more than adversaries, and the deep irony of the safety-first lab becoming the first casualty of a national security directive.Covered this episode: export controls applied to AI for the first time, why benchmarks are becoming "functionally useless," the marketing-hype trap of "uniquely capable" mo...
2026-07-1523 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastMeta AI Account Takeovers & AI-Discovered Zero-Days | Episode 6Hosts Rachel James and Dr. Bryan Nakayama break down a prompt-injection flaw that let attackers hijack Instagram accounts through Meta's AI support assistant — and a new Google report showing threat actors likely using AI to find and exploit a zero-day. The lesson: think hard about how much agency you hand your AI before you deploy it.Covered this episode: what "threat actors" and "zero-days" really mean, the Air Canada chatbot that invented a discount and lost in court, and why "just because you can, doesn't mean you should."Hosted by Rachel James and Dr. Bryan Na...
2026-07-1422 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastMITRE ATLAS vs. OWASP Top 10 for LLM Applications | Episode 5MITRE, ATLAS, OWASP, NIST — do security leaders really need to learn three new frameworks to defend their AI systems? In this episode of the Threat Intelligence Podcast, Rachel James and Dr. Brian Nakayama, volunteer leads in the OWASP GenAI Security Project, unpack the difference between MITRE ATLAS (Adversarial Threat Landscape for Artificial Intelligence Systems) and the OWASP Top 10 for LLM Applications, and where each fits relative to binding regulation like the EU AI Act and guidance like NIST's AI RMF.The hosts frame ATLAS as the "how" — a threat-intelligence-driven model of tactics, techniques, and procedures adversaries use agai...
2026-07-0921 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastStandalone Complex or Viber Crime? | Episode 4Is Gen AI actually turning script kiddies into nation-state hackers, or is that just movie-plot paranoia? In this episode of the Threat Intelligence Podcast, Rachel James and Brian Nakayama, volunteer leads in the OWASP GenAI Security Project, break down a new empirically-grounded paper — Standalone Complex or Viber Crime by Hughes, Collier, and Thomas — that studies how criminal actors are actually using generative AI across dark web and cybercrime forums.The conversation explores the paper's two framing extremes: "standalone complex" (an AI-powered hacking bot autonomously laying waste to organizations) versus "viber crime" (low-effort, vibe-coded criminal activity). Neither is materi...
2026-07-0920 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastPrompt Injection: The AI Attack Hiding in Plain Sight | Episode 3In this episode of The Threat Intelligence Podcast, Brian Nakayama and Rachel James of the OWASP GenAI Security Project about one of the most common and misunderstood threats facing AI systems: prompt injection.The conversation begins with the unusual story of Grok, Bankerbot, and DRB tokens, where an attacker reportedly used Morse code to bypass safeguards and trigger an automated cryptocurrency transaction. Brian explains how this incident illustrates a core weakness of large language models: they are designed to follow instructions, even when those instructions are disguised, encoded, or hidden in ways traditional filters may miss.Rachel connects the...
2026-06-0934 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastAI’s Zero-Day Wake-Up Call: What Mythos Means for Cyber Defence | Episode 2In this episode of The Threat Intelligence Podcast, Rachel James and Brian Nakayama of the OWASP GenAI AI Threat Intelligence Initiative about Anthropic’s Mythos model and the changing role of AI in vulnerability discovery.Rachel explains how earlier AI models offered limited value to attackers unless the user already had significant technical expertise. Those systems could help with pieces of a task, but they struggled to reason through vulnerabilities or generate reliable exploit paths on their own. Mythos, by contrast, appears to demonstrate a more advanced ability to analyze source code, understand how functions behave, identify weaknesses, and as...
2026-06-0229 minSecurity Weekly Podcast Network (Audio)
Security Weekly Podcast Network (Audio)AppSec Conversations on Agents, LLMs, and OWASP from RSAC - Merritt Maxim, Scott Clinton, Janet Worthington - ASW #384We showcase recordings from this year's RSAC. At RSAC Conference 2026, Scott Clinton, Co-Chair and co-founder of the OWASP GenAI Security Project, shares insights from the project’s latest research, including new landscape guides and evolving approaches to securing generative and agentic AI systems. The conversation explores critical gaps in GenAI data security, the rise of AI-assisted development, and the immense growth of the OWASP community and sponsor ecosystem. Looking ahead, he outlines the most urgent risks and priorities shaping AI and agentic security in 2026. Then Merritt Maxim discusses how AI is affecting Identity and Access Ma...
2026-05-2659 minApplication Security Weekly (Video)
Application Security Weekly (Video)AppSec Conversations on Agents, LLMs, and OWASP from RSAC - Scott Clinton, Janet Worthington, Merritt Maxim - ASW #384We showcase recordings from this year's RSAC. At RSAC Conference 2026, Scott Clinton, Co-Chair and co-founder of the OWASP GenAI Security Project, shares insights from the project's latest research, including new landscape guides and evolving approaches to securing generative and agentic AI systems. The conversation explores critical gaps in GenAI data security, the rise of AI-assisted development, and the immense growth of the OWASP community and sponsor ecosystem. Looking ahead, he outlines the most urgent risks and priorities shaping AI and agentic security in 2026. Then Merritt Maxim discusses how AI is affecting Identity and Access Management...
2026-05-2659 minSecurity Weekly Podcast Network (Video)
Security Weekly Podcast Network (Video)AppSec Conversations on Agents, LLMs, and OWASP from RSAC - Scott Clinton, Janet Worthington, Merritt Maxim - ASW #384We showcase recordings from this year's RSAC. At RSAC Conference 2026, Scott Clinton, Co-Chair and co-founder of the OWASP GenAI Security Project, shares insights from the project's latest research, including new landscape guides and evolving approaches to securing generative and agentic AI systems. The conversation explores critical gaps in GenAI data security, the rise of AI-assisted development, and the immense growth of the OWASP community and sponsor ecosystem. Looking ahead, he outlines the most urgent risks and priorities shaping AI and agentic security in 2026. Then Merritt Maxim discusses how AI is affecting Identity and Access Management...
2026-05-2659 minApplication Security Weekly (Audio)
Application Security Weekly (Audio)AppSec Conversations on Agents, LLMs, and OWASP from RSAC - Merritt Maxim, Scott Clinton, Janet Worthington - ASW #384We showcase recordings from this year's RSAC. At RSAC Conference 2026, Scott Clinton, Co-Chair and co-founder of the OWASP GenAI Security Project, shares insights from the project's latest research, including new landscape guides and evolving approaches to securing generative and agentic AI systems. The conversation explores critical gaps in GenAI data security, the rise of AI-assisted development, and the immense growth of the OWASP community and sponsor ecosystem. Looking ahead, he outlines the most urgent risks and priorities shaping AI and agentic security in 2026. Then Merritt Maxim discusses how AI is affecting Identity and Access Management...
2026-05-2659 minThe Threat Intelligence Podcast
The Threat Intelligence PodcastMythos, AI Vulnerability Discovery, and the Shrinking Window to Patch | Episode 1In this episode of the Threat Intelligence Podcast, Rachel James and Brian Nakayama, volunteer leads in the OWASP GenAI AI Threat Intelligence Initiative, about Anthropic’s Mythos model and its implications for cybersecurity.The conversation explores how frontier AI models are advancing from simple “spray and pray” code generation toward deeper reasoning over source code, vulnerability discovery, and exploit construction. Rachel explains how this progression aligns with earlier research showing that older models could assist knowledgeable operators but lacked the reasoning needed to independently identify and weaponize vulnerabilities. Mythos appears to represent a meaningful step forward, particularly in whi...
2026-05-2624 minSecurity Weekly Podcast Network (Audio)
Security Weekly Podcast Network (Audio)Keeping Up With the OWASP GenAI Project - Scott Clinton - ASW #381Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the appsec community for sharing effective ways to keep systems secure. Scott Clinton shares the latest progress on the the project, its roadmap for the year, and how appsec practitioners can shape its future. Resources: https://genai...
2026-05-051h 09Application Security Weekly (Video)
Application Security Weekly (Video)Keeping Up With the OWASP GenAI Project - Scott Clinton - ASW #381Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the appsec community for sharing effective ways to keep systems secure. Scott Clinton shares the latest progress on the the project, its roadmap for the year, and how appsec practitioners can shape its future. Resources: https://genai...
2026-05-051h 09Application Security Weekly (Audio)
Application Security Weekly (Audio)Keeping Up With the OWASP GenAI Project - Scott Clinton - ASW #381Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the appsec community for sharing effective ways to keep systems secure. Scott Clinton shares the latest progress on the the project, its roadmap for the year, and how appsec practitioners can shape its future. Resources: https://genai...
2026-05-051h 09Security Weekly Podcast Network (Video)
Security Weekly Podcast Network (Video)Keeping Up With the OWASP GenAI Project - Scott Clinton - ASW #381Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the appsec community for sharing effective ways to keep systems secure. Scott Clinton shares the latest progress on the the project, its roadmap for the year, and how appsec practitioners can shape its future. Resources: https://genai...
2026-05-051h 09Curiouser & Curiouser
Curiouser & CuriouserSecuring Agentic AI: The OWASP ApproachAgentic AI is moving fast. So are the risks.Mo talks with Steve Wilson (Chief AI and Product Officer at Exabeam and Founder and Co-chair of the OWASP GenAI Security Project) about OWASP’s approach to agentic AI security, including prompt injection, guardrails, and what it means to keep humans in the loop as agents scale.🔗 OWASP GenAI Project: https://genai.owasp.org 📘 The Developer’s Playbook for Large Language Model Security (O’Reilly): https://www.oreilly.com/library/view/the-developers-playbook/9781098162191/🔗 Podcast: https://alice.io/podcastFollow the sho...
2026-02-2444 minApplication Security Weekly (Video)
Application Security Weekly (Video)Modern AppSec: OWASP SAMM, AI Secure Coding, Threat Modeling & Champions - Sebastian Deleersnyder, James Manico, Adam Shostack, Dustin Lehr - ASW #362Using OWASP SAMM to assess and improve compliance with the Cyber Resilience Act (CRA) is an excellent strategy, as SAMM provides a framework for secure development practices such as secure by design principles and handling vulns. Segment Resources: https://owaspsamm.org/ https://cybersecuritycoalition.be/resource/a-strategic-approach-to-product-security-with-owasp-samm/ As genAI becomes a more popular tool in software engineering, the definition of "secure coding" is changing. This session explores how artificial intelligence is reshaping the way developers learn, apply, and scale secure coding practices — and how new risks emerge when machines start generating the code themselves. We'll dive in...
2025-12-231h 07Security Weekly Podcast Network (Video)
Security Weekly Podcast Network (Video)Modern AppSec: OWASP SAMM, AI Secure Coding, Threat Modeling & Champions - Sebastian Deleersnyder, James Manico, Adam Shostack, Dustin Lehr - ASW #362Using OWASP SAMM to assess and improve compliance with the Cyber Resilience Act (CRA) is an excellent strategy, as SAMM provides a framework for secure development practices such as secure by design principles and handling vulns. Segment Resources: https://owaspsamm.org/ https://cybersecuritycoalition.be/resource/a-strategic-approach-to-product-security-with-owasp-samm/ As genAI becomes a more popular tool in software engineering, the definition of "secure coding" is changing. This session explores how artificial intelligence is reshaping the way developers learn, apply, and scale secure coding practices — and how new risks emerge when machines start generating the code themselves. We'll dive in...
2025-12-231h 07Security Weekly Podcast Network (Audio)
Security Weekly Podcast Network (Audio)Modern AppSec: OWASP SAMM, AI Secure Coding, Threat Modeling & Champions - Sebastian Deleersnyder, Dustin Lehr, James Manico, Adam Shostack - ASW #362Using OWASP SAMM to assess and improve compliance with the Cyber Resilience Act (CRA) is an excellent strategy, as SAMM provides a framework for secure development practices such as secure by design principles and handling vulns. Segment Resources: https://owaspsamm.org/ https://cybersecuritycoalition.be/resource/a-strategic-approach-to-product-security-with-owasp-samm/ As genAI becomes a more popular tool in software engineering, the definition of “secure coding” is changing. This session explores how artificial intelligence is reshaping the way developers learn, apply, and scale secure coding practices — and how new risks emerge when machines start generating the code themselves. We’ll dive int...
2025-12-231h 07Application Security Weekly (Audio)
Application Security Weekly (Audio)Modern AppSec: OWASP SAMM, AI Secure Coding, Threat Modeling & Champions - Sebastian Deleersnyder, Dustin Lehr, James Manico, Adam Shostack - ASW #362Using OWASP SAMM to assess and improve compliance with the Cyber Resilience Act (CRA) is an excellent strategy, as SAMM provides a framework for secure development practices such as secure by design principles and handling vulns. Segment Resources: https://owaspsamm.org/ https://cybersecuritycoalition.be/resource/a-strategic-approach-to-product-security-with-owasp-samm/ As genAI becomes a more popular tool in software engineering, the definition of "secure coding" is changing. This session explores how artificial intelligence is reshaping the way developers learn, apply, and scale secure coding practices — and how new risks emerge when machines start generating the code themselves. We'll dive in...
2025-12-231h 07Security Weekly Podcast Network (Video)
Security Weekly Podcast Network (Video)Inside the OWASP GenAI Security Project - Steve Wilson - ASW #352Interest and participation in the OWASP GenAI Security Project has exploded over the last two years. Steve Wilson explains why it was important for the project to grow beyond just a Top Ten list and address more audiences than just developers. He also talks about how the growth of AI Agents influences the areas that appsec teams need to focus on. Whether apps are created by genAI or directly use genAI, the future of securing software is going to be busy. Resources https://genai.owasp.org https://genai.owasp.org/llm-top-10/ LLM security book on Amazon...
2025-10-141h 07Security Weekly Podcast Network (Audio)
Security Weekly Podcast Network (Audio)Inside the OWASP GenAI Security Project - Steve Wilson - ASW #352Interest and participation in the OWASP GenAI Security Project has exploded over the last two years. Steve Wilson explains why it was important for the project to grow beyond just a Top Ten list and address more audiences than just developers. He also talks about how the growth of AI Agents influences the areas that appsec teams need to focus on. Whether apps are created by genAI or directly use genAI, the future of securing software is going to be busy. Resources https://genai.owasp.org https://genai.owasp.org/llm-top-10/ LLM security book on Amazon...
2025-10-141h 07Application Security Weekly (Video)
Application Security Weekly (Video)Inside the OWASP GenAI Security Project - Steve Wilson - ASW #352Interest and participation in the OWASP GenAI Security Project has exploded over the last two years. Steve Wilson explains why it was important for the project to grow beyond just a Top Ten list and address more audiences than just developers. He also talks about how the growth of AI Agents influences the areas that appsec teams need to focus on. Whether apps are created by genAI or directly use genAI, the future of securing software is going to be busy. Resources https://genai.owasp.org https://genai.owasp.org/llm-top-10/ LLM security book on Amazon...
2025-10-141h 07Application Security Weekly (Audio)
Application Security Weekly (Audio)Inside the OWASP GenAI Security Project - Steve Wilson - ASW #352Interest and participation in the OWASP GenAI Security Project has exploded over the last two years. Steve Wilson explains why it was important for the project to grow beyond just a Top Ten list and address more audiences than just developers. He also talks about how the growth of AI Agents influences the areas that appsec teams need to focus on. Whether apps are created by genAI or directly use genAI, the future of securing software is going to be busy. Resources https://genai.owasp.org https://genai.owasp.org/llm-top-10/ LLM security book on Amazon...
2025-10-141h 07Application Security Weekly (Audio)
Application Security Weekly (Audio)How OWASP's GenAI Security Project keeps up with the pace of AI/Agentic changes - Scott Clinton - ASW #348This week, we chat with Scott Clinton, board member and co-chain of the OWASP GenAI Security Project. This project has become a massive organization within OWASP with hundreds of volunteers and thousands of contributors. This team has been cranking out new tools, reports and guidance for practitioners month after month for over a year now. We start off discussing how Scott and other leaders have managed to keep up with the crazy rate of change in the AI world. We pivot to discussing some of the specific projects the team is working on, and finally discuss some...
2025-09-161h 08Application Security Weekly (Video)
Application Security Weekly (Video)How OWASP's GenAI Security Project keeps up with the pace of AI/Agentic changes - Scott Clinton - ASW #348This week, we chat with Scott Clinton, board member and co-chain of the OWASP GenAI Security Project. This project has become a massive organization within OWASP with hundreds of volunteers and thousands of contributors. This team has been cranking out new tools, reports and guidance for practitioners month after month for over a year now. We start off discussing how Scott and other leaders have managed to keep up with the crazy rate of change in the AI world. We pivot to discussing some of the specific projects the team is working on, and finally discuss some...
2025-09-161h 08Security Weekly Podcast Network (Audio)
Security Weekly Podcast Network (Audio)How OWASP's GenAI Security Project keeps up with the pace of AI/Agentic changes - Scott Clinton - ASW #348This week, we chat with Scott Clinton, board member and co-chain of the OWASP GenAI Security Project. This project has become a massive organization within OWASP with hundreds of volunteers and thousands of contributors. This team has been cranking out new tools, reports and guidance for practitioners month after month for over a year now. We start off discussing how Scott and other leaders have managed to keep up with the crazy rate of change in the AI world. We pivot to discussing some of the specific projects the team is working on, and finally discuss some...
2025-09-161h 08Security Weekly Podcast Network (Video)
Security Weekly Podcast Network (Video)How OWASP's GenAI Security Project keeps up with the pace of AI/Agentic changes - Scott Clinton - ASW #348This week, we chat with Scott Clinton, board member and co-chain of the OWASP GenAI Security Project. This project has become a massive organization within OWASP with hundreds of volunteers and thousands of contributors. This team has been cranking out new tools, reports and guidance for practitioners month after month for over a year now. We start off discussing how Scott and other leaders have managed to keep up with the crazy rate of change in the AI world. We pivot to discussing some of the specific projects the team is working on, and finally discuss some...
2025-09-161h 08Certified - AI Security Audio Course
Certified - AI Security Audio CourseEpisode 36 — OWASP GenAI/LLM Top 10This episode introduces the OWASP GenAI/LLM Top 10, a structured list of the most critical risks associated with generative AI and large language models. For certification purposes, learners must understand how OWASP adapts its long-standing methodology for web applications to the AI context, focusing on vulnerabilities such as prompt injection, insecure output handling, training data poisoning, and model theft. The exam relevance lies in knowing how these categories prioritize defensive focus and provide a common language for risk management. Mastery of the Top 10 allows candidates to quickly identify high-impact risks and connect them to appropriate technical and organizational controls.
2025-09-1522 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.44 Meeting Aug 27 2025: Initiatives, New Website, and Community GrowthThis meeting covers updates on OWASP’s GenAI Security Project, including improvements to the website for easier contributor onboarding, global events like the upcoming UAE hackathon, and plans for the OWASP virtual AppSec Security Summit in October. Other highlights include new tools, the CTI team’s Exploit Generation initiative, and the launch of the Deepfake Guide revision project. The session also welcomes new members and provides pointers on how to get involved with the project across various initiatives like Agentic AI, LLM security, and red teaming.
2025-09-0224 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.43 Meeting Aug 13 2025: Black Hat Recap, New Tools, and OWASP RoadmapThis meeting provides updates on OWASP’s GenAI Security Project, including highlights from Black Hat and DEF CON events, the launch of new tools like the FinBot CTF platform, and progress on important resources such as the GenAI Solutions Landscape and Agentic AI initiatives. The discussion also covers community engagement, growth metrics, and upcoming plans for the OWASP virtual conference in October. Participants share insights on onboarding contributors and continuing to scale AI security efforts globally.
2025-09-0235 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.42 Meeting Jul 30 2025: OWASP Initiatives, Agent Protection, and Black Hat PrepThis meeting covers key updates on OWASP’s AI security initiatives, including agent architecture, threat mitigation, and practical resources for securing AI systems. We discuss upcoming events at Black Hat and DEF CON, recent releases like the GenAI Solutions Landscape, and progress on AI security guidelines and frameworks. Participants also explore ways to contribute to the community and advance AI-driven security practices.
2025-09-0243 minThe Generative AI Security Podcast
The Generative AI Security PodcastExploring GenAI Security: Agentic Top 10, Threat Modeling & Community HackathonsJoin us on the latest episode of the GenAI Security Podcast as Aubrey King chats with John Sotiropoulos, co-lead of the Agentic Security Initiative. Dive deep into AI agent security, the groundbreaking Agentic Top 10 (coming soon!), and how the OWASP GenAI Security Project is shaping the future of safe AI development.Get insights on threat modeling, hackathons, innovative community initiatives, and how YOU can contribute to this growing global movement. Whether you’re in AI, cybersecurity, or just curious, there’s something here for everyone!📌 Learn more and get involved: OWASP GenAI SecurityDon’t forget to like, share, and subscribe...
2025-07-3121 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.41 Meeting Jul 16 2025: Roadmap, Black Hat Prep & Compass LaunchIn this episode of the OWASP Generative AI Security Project podcast, we dive into exciting updates and advancements in AI security. From the upcoming OWASP Compass launch to Black Hat and DEFCON preparations, this meeting spotlighted progress across initiatives like agentic security, the roadmap for future deliverables, and community efforts to enhance industry awareness.📌 Highlights include:🛠️ OWASP Compass 1.0: A strategic dashboard to guide AI adoption securely.🌍 Black Hat & DEFCON updates: New workshops, hackathons, and outreach efforts.🌟 Agentic Security: Threat modeling advancements and a preview of the upcoming Agentic Top 10 list.📋 Solutions Landscape: Expanding tools and resources for cybersecurity practitioners.🌐 Ready to get involve...
2025-07-1645 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.40 Meeting Jul 2 2025: OWASP Compass Tool & Exciting UN Week HighlightsDiscover the latest in AI and cybersecurity as we unpack cutting-edge tools and global collaborations. This episode introduces the OWASP Compass, a unique framework for operationalizing AI strategies, alongside highlights from UN Open Source Week and upcoming events like Black Hat and DEFCON.Whether you’re into red teaming, AI governance, or free training resources, this episode has something for everyone!📌 Learn more: OWASP GenAILet’s shape a safer AI-powered future!
2025-07-0245 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.39 Meeting Jun 18 2025: UN Panel, Compass Tool Progress & AI Red Teaming FrameworkCatch the latest updates from the OWASP GenAI Security Project, including global partnerships, tools, and groundbreaking AI security research:🔍 Key topics:UN Open Source Week: OWASP takes the stage to discuss AI security in supply chain and generative AI advancements.Compass Tool Update: Simplifying AI threat strategies with profiles and streamlined workflows.AI Incident Response Guide: Now open for core team review—aiming for a July release.AI Red Teaming Framework: New initiatives to enhance vulnerability testing in generative AI systems.Stay informed as we push the boundaries of AI security innovation!#OWASP #GenAI #AISecurity #CompassTool #RedTeaming #UNOpenSource #GenerativeAI
2025-06-2027 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.38 Meeting Jun 04 2025: Compass Tool, AI Incident Response & Exploit Generation AdvancesThis episode dives into the latest milestones from the OWASP GenAI Security Project, focusing on AI security tools, responses, and emerging challenges in the world of generative AI:🔍 Key topics:Compass Tool Updates: Streamlining AI threat identification and strategy building.AI Incident Response Guide: A specialized framework for preparing and managing AI-enabled breaches.Exploit Generation Research: Advancing LLM and agentic AI testing to benchmark cybersecurity risks.Don’t miss actionable insights from evolving initiatives like red teaming and agentic security. Stay updated on the forefront of AI safety!#AISecurity #OWASP #GenAI #AIIncidentResponse #CompassTool #ExploitGeneration
2025-06-2030 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.37 Meeting May 21 2025: Compass Tool, AI Red Teaming, and Post-RSA InsightsIn this episode, we discuss the latest developments in AI security from the OWASP GenAI Security Project, featuring updates on the Compass Tool, AI Red Teaming efforts, and the evolving landscape of generative AI risks.🔍 Key topics:Compass Tool: An operationalized version of the CISO checklist for prioritizing generative AI threats.AI Red Teaming Handbook: Progress on testing frameworks for LLMs and AI systems.Post-RSA reflections: Key takeaways and future initiatives in AI security.Stay ahead in the dynamic field of AI security with these actionable insights!#OWASP #GenAI #AISecurity #AIRedTeaming #CompassTool #RSA2025
2025-06-2031 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.36 Meeting May 07 2025: AI Security Trends, Agentic AI, and Post-RSA UpdatesCatch the latest updates from the OWASP GenAI Security Project following RSA, including discussions on AI security trends, Agentic AI workflows, and project highlights like the Compass Tool.🛡️ Key insights include:The evolving intersection of AppSec and LLM security.Updates on Agentic AI workshops and Peer-reviewed AI guidance.Behind the scenes of OWASP’s initiatives shaping the future of generative AI security.Stay informed on the latest in AI security and learn how to get involved! 🌍#AISecurity #OWASP #GenAI #AgenticAI #RSA2025 #RedTeaming #AppSec
2025-06-2052 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.35 Meeting Apr 23 2025: Agentic AI, Red Teaming & RSA 2025 HighlightsIn this podcast, we dive into key updates from the OWASP GenAI Security Project, including the latest on Agentic AI, red teaming best practices, upcoming events at RSA 2025, and exciting tools like the Compass for AI security maturity. 🌐🛡️ Highlights:Insights into red teaming vulnerabilities and testing strategies.The importance of Agentic AI security frameworks.Exclusive RSA 2025 workshops, parties, and live streams.Tools to enhance AI governance and navigate AI risks effectively.Stay ahead in the AI security game!#AISecurity #OWASP #GenAI #RSA2025 #RedTeaming #AgenticAI
2025-06-2048 minThe Generative AI Security Podcast
The Generative AI Security PodcastAre Your Red Teaming Efforts Giving Bad Actors An Advantage? GenAI SecurityIn this episode of the Generative AI Security Podcast, we sit down with Disesdi Susanna Cox, from the OWASP AI Exchange, to explore the cutting-edge of AI security:🔍 Key topics include:The OWASP AI Exchange as a resource for understanding AI security threats.Fascinating insights on red teaming, adversarial attacks, and why full coverage may be mathematically impossible.How generative AI adoption intersects with predictive AI use cases and security risks.Learn why staying ahead of AI security trends is crucial and how tools like the OWASP AI Exchange can help!#AISecurity #GenerativeAI #OWA...
2025-05-2317 minThe Generative AI Security Podcast
The Generative AI Security PodcastOWASP Project Rebrand, RSA Conference Highlights - GenAI Security Podcast Ep.7Welcome to Episode 7 of the Generative AI Security Podcast! 🚀 This week, we dive into the rebranding of the Gen AI Security Project, upcoming highlights at RSA Conference 2023—including a must-attend Gen AI party—and discussions on cutting-edge initiatives like agentic security and red teaming guides. Join Aubrey, Steve, and Scott as they cover the evolution of this OWASP project, its impact on generative AI security, and what’s next for the community. Don’t forget to like, subscribe, and stay updated on all the latest content!
2025-04-1816 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.34 Meeting Apr 09 2025: RSA Summit, New Compass Project, Community UpdatesJoin host Scott Clinton and cybersecurity community members for the latest OWASP GenAI Security Project meeting. In this episode, the team shares key updates on their upcoming activities at the RSA Conference—including a half-day summit, agentic security workshop, and special networking opportunities. Scott emphasizes community engagement, while Sandy Dunn introduces the newly established Compass Project, dedicated to operationalizing governance and security strategies in practical, effective ways.Additionally, the episode covers project updates on AI incident response with Bryan Nakayama, translation efforts for wider global accessibility, and other initiatives to build cohesive, community-driven resources. This meeting demonstrates OWASP's ongoing co...
2025-04-1644 minThe Generative AI Security Podcast
The Generative AI Security PodcastContinuous Red Teaming for AI: Insights from OWASP Experts - GenAI Security Ep.6In this episode of the OWASP GenAI Security Podcast, Aubrey sits down with Ante and Kris from Splx to discuss the importance of continuous red teaming for AI applications. As AI evolves with multimodal systems, agent frameworks, and retrieval-augmented generation (RAG), proactive security testing becomes essential to address vulnerabilities like jailbreaks, data poisoning, and alignment shifts.Learn how integrating automated red teaming processes and collaborating closely with security teams can help organizations stay ahead of threats. Don’t miss this deep dive into the latest strategies for safeguarding AI applications in production and beyond.
2025-04-0426 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.33 Meeting Mar 26 2025 - Project Updates: Governance, Sponsorship & GrowthIn this episode, join Scott Clinton, Steve Wilson, John Sotiropoulos, and Aubrey King as they discuss the latest updates and achievements in the OWASP GenAI Security Project. From the introduction of new governance structures to insights on sponsorship growth, this episode provides an in-depth look at how the project is evolving to tackle the challenges in AI security.Learn about the various initiatives and milestones, including the success of the Agentic AI initiative, the upcoming events at RSA, and the impressive community engagement metrics. Whether you're a cybersecurity professional, AI enthusiast, or someone interested in contributing to the project...
2025-03-2657 minThe Generative AI Security Podcast
The Generative AI Security PodcastExploring Agentic AI Security with OWASP: Insecure Agent Hackathon Apr 1 In NYCIn this episode of our podcast, Aubrey from the OWASP GenAI Security Project sits down with Ali Howe, the founder of Growth Cyber and contributor to the project. Alie shares her journey from software engineering to becoming a vCISO, emphasizing the importance of AI security and SOC 2 compliance for startups. She discusses the upcoming OWASP Insecure Agents Hackathon in New York City, where developers will explore building AI agents with a focus on identifying and mitigating security threats.Join us to learn more about the OWASP Gen AI Security Project, the significance of AI security in modern startups, and...
2025-03-2515 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.32 Meeting Mar 12 2025: AI Red Teaming, Securing AI Models, and Best Practices in AI SecurityIn this episode, Scott Clinton leads the discussion on the latest trends and challenges in the AI security landscape. They kick things off with a friendly catch-up before diving into important topics like AI red teaming, the security of AI models, and the best practices for ensuring robust AI security frameworks.Throughout the discussion, our experts share their insights on how to tackle the evolving threats in the AI space. From the lack of security measures in many organizations to the innovative approaches being developed to counter these threats, this episode is a treasure trove of information for anyone...
2025-03-251h 00GenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.31 Meeting Feb 26 2025: Red Teaming Guide Updates, Agentic Security InsightsWelcome to our latest podcast episode where we delve into the nuances of AI security and the exciting developments in the field. In this episode, we discuss the recent meeting of our AI security team, highlighting key projects such as the Red Teaming Guide, the Agent Security Insights (ASI) document, and the ongoing efforts to translate and refine our resources for global use. Steve Wilson, Sandy Dunn, and Scott Clinton share their insights on the latest advancements and the collaborative efforts that are driving the future of AI security.Join us as we explore the intricacies of defining AI...
2025-03-1149 minThe Generative AI Security Podcast
The Generative AI Security PodcastSandboxing AI Models with Dyana & OWASP Top 10 for LLM Apps - Ep.4Welcome back to our Generative AI Security Podcast! In this episode, Aubrey sits down with Ads Dawson, a respected member of the AI community, to delve into the OWASP Top Ten for LLM Applications and Generative AI. They discuss the latest security challenges and showcase Dyana, an open-source utility developed by Dreadnode for profiling and securing machine learning models.Ads gives a comprehensive demo of Diana, explaining its functionalities and how it can sandbox and profile a wide range of files, including models from Hugging Face. Discover how Diana can help detect backdoored models and provide detailed insights into...
2025-03-0622 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp.30 Meeting Feb 12 2025: AI Security Guidelines, Agentic Security, RSA SummitJoin us for an insightful discussion in our latest podcast episode featuring our core team and many others from the AI security community. This episode dives deep into various exciting topics, including the introduction of new AI security guidelines, the advancements in agentic security, and the latest developments in AI red teaming. We explore the collaborative efforts in creating practical and consumable security documentation, the impact of AI security standards alignment, and the roadmap for future AI security projects.In addition to these discussions, we also highlight the upcoming AI Security Summit at RSA Conference, the integration of AI...
2025-02-2553 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp. 29: Meeting Jan 29 2025: Glossary Initiative, RSA Summit, and New SponsorsJoin us for an engaging episode where the OWASP LLM and Gen AI Project Team discuss key initiatives, updates, and collaborative efforts. This episode dives into various topics such as the ongoing development of the Agentic Security Landscape, the importance of creating a standardized glossary for AI terminology, and the exciting collaborations with organizations like IBM and the Cloud Security Alliance. The team also explores the potential of producing educational videos to enhance understanding of AI concepts and terms.In this meeting, the team emphasizes the need for consensus and community feedback in refining AI definitions, while also discussing...
2025-02-2456 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp. 28: Meeting Jan 15 2025 - Red Teaming, Deepfake, RSA 2025 Updates And MoreJoin the core team as they dive into a comprehensive discussion on recent workshops, AI advancements, and the significance of industry conferences. This episode unpacks the latest feedback from cybersecurity sessions and sets the stage for RSA 2025 and other upcoming events. Scott Clinton and Bryan Nakayama add depth with insights into AI red teaming and deepfake initiatives as well as community growth metrics. Don't miss out on this engaging conversation that bridges the gap between cybersecurity strategy and practical implementation. Subscribe for more expert insights!
2025-01-2159 minThe Generative AI Security Podcast
The Generative AI Security PodcastExploring AI Security: Red Teaming & Offensive Agents with Ads | GenAI Security Ep.3Join us for the third episode of our podcast, where Aubrey from the OWASP Top Ten for Large Language Model Applications and Generative AI dives into the evolving world of AI security. In this episode, we chat with Ads, a seasoned AI security researcher from Dreadnode, who shares his journey from network engineering to AI security. Gain insights into the latest trends in AI red teaming, offensive agents, and the exciting developments at Dreadnode. Explore the fascinating world of AI security with real-world examples, the importance of agentic AI, and how innovative tools like RoboPages and Burpference...
2025-01-0932 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEp. 27: Meeting Dec 18 2024 - OWASP Recognition, AI Red Teaming, RSA And MoreWelcome to our latest episode, recorded on December 18th, where we dive into the exciting progress and future plans for our project as we wrap up 2024. We discuss the incredible work done by our community, the recognition from the OWASP Foundation, and our ambitious roadmap for 2025. Highlights include updates on the project's progress, insights from our check-in with Andrew, the Executive Director of OWASP, and plans for promoting the project and increasing community engagement. We also cover the launch of our new AI Red Teaming Initiative and updates to the AI cybersecurity and governance checklist.We touch on our...
2024-12-191h 02The Generative AI Security Podcast
The Generative AI Security PodcastEffective AI Red Teaming Best Practices With Krishna Sankar - GenAI Security Ep.2In this second episode of our podcast series, we introduce the Red Teaming Initiative with special guest Krishna Sankar. Discover the nuances of red teaming in the context of generative AI, explore best practices, and understand what it takes to develop a mature red teaming strategy. Krishna also shares his rich background in autonomous systems, AI in financial services, and his passion for Legos! Don't miss out on this informative discussion that also touches on the exciting (and somewhat daunting) concept of Artificial General Intelligence (AGI) and its implications. For the latest insights and updates in generative AI security...
2024-12-1235 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 26: Meeting December 4 2024 Launch Updates, New GenAI Security Podcast And MoreWelcome to the latest bi-weekly meeting for the OWASP Top Ten for Generative AI and Application Security, recorded on December 4th, 2024. Join us as we dive into key updates, project developments, and community engagement activities. This meeting covers updates on meeting link changes, recent launch statistics, social media metrics, and community growth. We also discuss new initiatives like the upcoming podcast series, LinkedIn engagement strategies, future webinars, and our plans for 2025 outreach. We highlight the progress on the Red Teaming document, data security best practices white paper, and explore translation services for broader accessibility. Additionally, we share...
2024-12-0429 minThe Generative AI Security Podcast
The Generative AI Security Podcast2025 LLM Apps Top 10, Evolving AI Architectures - GenAI Security Ep.1Welcome to the first episode of the Gen AI Security Podcast! 🎉 Join Aubrey King, Sandy Dunn, and Scott Clinton as they discuss Thanksgiving plans and dive into the OWASP Top Ten for LLM apps. We'll cover our recent 2025 release, deepfake guidance, and evolving AI architectures like RAG. Perfect for a mix of holiday cheer and cutting-edge cybersecurity insights! 🔗 Resources: OWASP GenAI Project: genai.owasp.org #GenAISecurity #Cybersecurity #Podcast #Thanksgiving #AI #OWASP Theme song, 'Crumbling Castle,' freely usable by King Gizzard And The Lizard Wizard, as per https://kinggizzardandthelizardwizard.com/bootlegger.
2024-11-2829 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 25: Meeting November 20 2024 Version 2025 Released This WeekThe session covers key updates and lively discussions among team members. Steve Wilson welcomes attendees and discusses recent travels and the prepared slide deck. The team celebrates the release of the new Top 10 list and its positive reception. Scott Clinton shares success stories and goals from the sponsorship program, while social media growth, project roadmap, and community contributions are highlighted. Krishna updates on the newsletter and future plans for webinars and outreach. The growth of the solutions landscape and the onboarding of a new web team are also discussed. The team brainstorms new initiatives, including workshops and virtual events...
2024-11-2145 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 24: Meeting November 6 2024 Deepfake Guidance, Solutions Landscape And MoreJoin us for an engaging meeting discussing the November 6th edition of the OWASP Top 10 for LLM (Large Language Model) applications. Steve Wilson leads the session, providing updates on the latest developments, including the release candidate, feedback collection, and expectations for the final version. Key points include the importance of the OWASP Top 10 list for 2025, feedback on errors and formatting, and insights into the traction generated by recent press releases and media coverage. The team also discusses the solutions landscape document, the searchable directory of solutions, and upcoming announcements for the new OWASP Top 10 list. Contributions from team members...
2024-11-0822 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 23: Meeting October 23 2024 Finalizing The 2025 Top 10 And More!In this meeting, the team finalizes the 2025 version of the OWASP Top 10 list for large language models (LLMs), highlighting key updates to the entries and ongoing efforts to refine the document's graphical layout. They also discuss the integration of the solutions catalog, which now features over 40 contributions from both open-source and commercial entities. Additionally, plans for a robust PR and media outreach campaign are outlined, including potential briefings with press and analysts, and the announcement of a sponsorship program in November. The team is also considering hosting a virtual event in December to highlight the new 2025 list and other...
2024-10-2817 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 22: Meeting October 9 2024 Prompt Injection Redefined, AI Bill Of MaterialsCatch up on the latest OWASP Top 10 for Large Language Models (LLMs) meeting! Russell Tait and Rachel discuss AI Incident response, while Steve Wilson updates on transitioning to the 2024 version. Key topics include prompt injection redefinition, red teaming progress, AI Bill of Materials proposal, and updates on the Deepfake Guide, AI-enhanced Cyber Attack Guidance, and exploit generation for AI. Sandy Dunn provides an AI Security Checklist update and proposes a centralized definitions page, and Scott Clinton announces the new Center of Excellence guide and encourages contributions to the Solutions Guide. For more details, check out the Deepfake Guide and...
2024-10-2558 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 21: Meeting September 11 2024 Prompt Leakage, Agent Interaction, Supply ChainIn our recent session, we discussed the ever-evolving landscape of AI and machine learning security. Key highlights include: 1. Prompt Leakage: Addressing vulnerabilities where AI systems inadvertently disclose sensitive information. 2. Agent Interaction Risks: Focusing on excessive agency and the complexities of multi-agent systems. 3. Supply Chain Vulnerabilities: Ensuring robust security measures in AI development pipelines.
2024-09-1357 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 20: Meeting August 28 2024 Defining AI Incidents, Deep Fake GuidanceIn our recent meeting, we covered crucial topics such as defining AI incidents, publishing deep fake guidance, and innovative research on AI exploitation. Our community continues to drive forward with impactful initiatives. Also, a special mention to our beautiful new HQ in Colorado! 🌄 #AI #CyberSecurity #OWASP
2024-09-1353 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 19: Meeting August 15, 2024 AI-Enhanced Cyber Attack ResponsesIn our recent meeting, we explored several key topics, including AI-enhanced cyber attack responses, the importance of automated PDF generation for documentation, and welcoming new members to our community. These discussions are crucial for staying ahead in AI and cybersecurity. Dive in and contribute to shaping the future of AI security with us. #AI #CyberSecurity #OWASP #TechInnovation
2024-09-1334 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 18: Meeting August 1 2024: Multi-Agent Architectures In AIIn our recent meeting, we explored the evolving landscape of agentic workflows and multi-agent architectures in AI. From discussing the orchestration of tools to the complexities of fully autonomous agents, our team is at the forefront of AI innovation. Dive into the discussion, share your insights, and help shape the future of AI governance. #AI #MachineLearning #AIInnovation #AIResearch
2024-09-1357 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 17: Core Member Meeting July 10 2024 - v2.0 New Threat ConversationWe took a break from the standard meeting and had a meeting of the core member team to hash out some of the new threats that have come up in conversation for v2.0 ranking.
2024-07-1158 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 16: Meeting June 20 2024 - v2.0 Voting, Conferences & CFPs, PDF PipelinesThe team discussed the progress of the large language models expert group project, focusing on the voting phase for new entries and the future publication. They also discussed the importance of the top 10 list, the outreach roadmap, and the need for upcoming calls for papers. Lastly, they explored potential solutions for managing multiple PDF pipelines, the use of templating, and the team's presence at an upcoming conference in Lisbon.
2024-06-2040 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 15: Meeting June 6 2024 - v2.0 Candidates, Top AI Tools List, CSA AI Summit And MoreThe team discussed the call for new vulnerability candidates for the OASP top 10 for large language models expert group, the challenges of accommodating all nominations for the AI Safety Institute's task force, and the ongoing process of creating a list of top AI tools. They also reviewed the progress of the organization's sponsorship program, plans for outreach, and the upcoming publication of a blog based on research from the University of Illinois. Lastly, they discussed the upcoming CSA AI summit, improving existing vulnerabilities, and the idea of creating a top 20 list to recognize emerging vulnerabilities.
2024-06-0854 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 14: Meeting May 23 2024 - RSA Recap, New Website, v2.0 EffortsThis week, Scott leads the bi-weekly meeting for May 23, 2004. We recap the RSA happenings, talk about the new website and get a bit of an update on the v2.0 efforts! Check out Episode 14 of the Bi-weekly Meeting Podcast!
2024-05-2334 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 13: Meeting April 25 2024 - v2 Updates, RSA Planning, New WebsiteSteve Wilson's back to lead the discussion for our April 25 2024 meeting for Episode 13. We talk about the v2 updates - even some survey response discussions. RSA Planning was a significant topic as well, as it's coming up quickly. We also talked the new website efforts and a whole lot more.
2024-04-2952 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 12: Meeting April 11 2024 - RSA, OWASP Media BlitzThe team, led by Scott, discussed upcoming activities including the RSA conference, a virtual summit on AI, and a website refresh. They also reviewed the success of their recent social media campaign and planned for future promotions. Lastly, they addressed the improvement of their data gathering methodology and looked forward to the next week's catch-up through Slack.
2024-04-1513 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 11: Meeting March 28 2024 - OWASP Top 10 For LLM ApplicationsThis month was huge. We talked about the returning core members and early data from our volunteer interest survey, as well as possible charter expansion. We've also got an AI summit coming up at RSA that is not to miss! Also, the leads gave reports, too!
2024-03-2852 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsEpisode 10: Meeting March 14 2024 - OWASP Top 10 For LLM ApplicationsSteve wasn't able to make the meeting this week, so Sandy Dunn ran the meeting. We talked about how to share any speaking opportunities you may have with the team and had great discussion around prompt injection and "AI-washing" from vendors.
2024-03-1540 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting Announcement! Thursday March 14, 2024 - 11am Eastern / 8am PacificSet your Alexa alarms, AI Community! We've got a meeting this Thursday and want to see YOU there! Meetings Link: https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/wiki/Meetings
2024-03-1300 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting February 29, 2024 - OWASP Top 10 For LLM ApplicationsWe talked about the 2.0 Kickoff and introduced the concept for budget and sponsorship.
2024-03-1257 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting Announcement! Thursday, Feb. 29 2024 - 11am Eastern / 8am PacificWe've got a meeting this Thursday @ 8am Pacific / 11am Eastern. Set your clocks, #AISecurity aficionados!Meetings Link: https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/wiki/Meetings #AI #LLMTop10
2024-02-2800 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting February 15, 2024 - OWASP Top 10 For LLM ApplicationsHear from some new community members and get into a bit of the 2.0 brainstorming, as well as hearing from the leads. Impending release for the Security And Governance Checklist!
2024-02-1641 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting February 1, 2024 - OWASP Top 10 For LLM ApplicationsThe 2.0 Kickoff meeting! This is where we break it down a bit. We talk about the goals of the project, in terms of evangelism and planning for the next major release. We also get a rundown on activities for each of the leads. If you want to know a bit more about what our visibility is actually looking like or any data from our audience, we go over the early results on our end consumer survey!
2024-02-0552 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting Announcement! Thursday, Feb 1, 2024 - 11 AM Eastern / 8 AM PacificCome check out our bi-weekly meeting on February 1! ⁠https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/wiki/Meetings --- Send in a voice message: https://podcasters.spotify.com/pod/show/owasp-top-10-for-llm-apps/message
2024-02-0100 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting January 18, 2024 - OWASP Top 10 For LLM ApplicationsTalked about the reception of our first three translations, the forthcoming Security & Governance Checklist and the impending 2.0 release announcement. Join us every two weeks for the latest in our project.
2024-01-2228 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting Announcement! Thursday, Jan 18, 2024 - 11 AM Eastern / 8 AM PacificCome check out our bi-weekly meeting tomorrow, Jan 18! https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/wiki/Meetings
2024-01-1700 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting January 04, 2024 - OWASP Top 10 For LLM ApplicationsFirst meeting after the holiday season, so a bit short. We covered the podcast release, passing 1000 LinkedIn subscribers, talked about the new language translations forthcoming release, getting closer on the Security & Governance Checklist and much more!
2024-01-0421 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting December 21, 2023 - OWASP Top 10 For LLM ApplicationsOur Bi-Weekly Meeting!
2023-12-2230 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting December 7, 2023 - OWASP Top 10 For LLM ApplicationsOur Bi-Weekly meeting for Dec. 7 2023.
2023-12-2236 minGenAI Security Project Open Meetings
GenAI Security Project Open MeetingsMeeting November 9, 2023 - OWASP Top 10 For LLM ApplicationsThis is our meeting update for Nov. 9, 2023.
2023-12-2246 minThe Application Security Podcast
The Application Security PodcastSteve Wilson and Gavin Klondike -- OWASP Top Ten for LLM ReleaseThe first OWASP Top 10 for Large Language Model Applications gave developers and security teams a shared threat model for a rapidly changing technology. Project leaders Steve Wilson and Gavin Klondike walk through the inaugural list and explain why familiar controls need to be reconsidered around probabilistic systems. They cover prompt injection, insecure output handling, training-data poisoning, denial of service, supply-chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, and model theft. Along the way, they distinguish application risks from attacks on the underlying model and show how plugins and autonomous actions can enlarge the blast radius. The...
2023-10-3151 min