本日紹介した論文の一覧
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising
Delivery
http://arxiv.org/abs/2505.21499v1
M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained
Encrypted Traffic Classification with Unknown Pattern Discovery
http://arxiv.org/abs/2505.21462v1
Cryptography from Lossy Reductions: Towards OWFs from ETH, and Beyond
http://arxiv.org/abs/2505.21442v1
Enhancing JavaScript Malware Detection through Weighted Behavioral DFAs
http://arxiv.org/abs/2505.21406v1
Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks
through Expanding Strategy Space
http://arxiv.org/abs/2505.21277v1
JavaSith: A Client-Side Framework for Analyzing Potentially Malicious
Extensions in Browsers, VS Code, and NPM Packages
http://arxiv.org/abs/2505.21263v1
ColorGo: Directed Concolic Execution
http://arxiv.org/abs/2505.21130v1
Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
http://arxiv.org/abs/2505.21074v1
SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with
Heterogeneous LoRA
http://arxiv.org/abs/2505.21051v1
Uncovering Black-hat SEO based fake E-commerce scam groups from their
redirectors and websites
http://arxiv.org/abs/2505.21021v1
A Hitchhiker's Guide to Privacy-Preserving Cryptocurrencies: A Survey on
Anonymity, Confidentiality, and Auditability
http://arxiv.org/abs/2505.21008v1
Unveiling Impact of Frequency Components on Membership Inference Attacks
for Diffusion Models
http://arxiv.org/abs/2505.20955v1
IRCopilot: Automated Incident Response with Large Language Models
http://arxiv.org/abs/2505.20945v1
Towards a DSL for hybrid secure computation
http://arxiv.org/abs/2505.20912v1
Respond to Change with Constancy: Instruction-tuning with LLM for
Non-I.I.D. Network Traffic Classification
http://arxiv.org/abs/2505.20866v1
EarthOL: A Proof-of-Human-Contribution Consensus Protocol -- Addressing
Fundamental Challenges in Decentralized Value Assessment with Enhanced
Verification and Security Mechanisms
http://arxiv.org/abs/2505.20614v1
なお、ポッドキャスト内で紹介する内容は、各論文の概要を日本語で解説したもので、論文概要の著作権は論文著者に帰属します。
]]>