Description

本日紹介した論文の一覧

• RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
  http://arxiv.org/abs/2510.20768v1

• Learning to Triage Taint Flows Reported by Dynamic Program Analysis in
  Node.js Packages
  http://arxiv.org/abs/2510.20739v1

• SafeFFI: Efficient Sanitization at the Boundary Between Safe and Unsafe
  Code in Rust and Mixed-Language Applications
  http://arxiv.org/abs/2510.20688v1

• Risk Psychology & Cyber-Attack Tactics
  http://arxiv.org/abs/2510.20657v1

• Decentralized Exchange that Mitigate a Bribery Attack
  http://arxiv.org/abs/2510.20645v1

• Black Box Absorption: LLMs Undermining Innovative Ideas
  http://arxiv.org/abs/2510.20612v1

• AdaDoS: Adaptive DoS Attack via Deep Adversarial Reinforcement Learning
  in SDN
  http://arxiv.org/abs/2510.20566v1

• Adversary-Aware Private Inference over Wireless Channels
  http://arxiv.org/abs/2510.20518v1

• On the cybersecurity of LoRaWAN-based system: a Smart-Lighting case
  study
  http://arxiv.org/abs/2510.20494v1

• Transferable Black-Box One-Shot Forging of Watermarks via Image
  Preference Models
  http://arxiv.org/abs/2510.20468v1

• MAC Aggregation over Lossy Channels in DTLS 1.3
  http://arxiv.org/abs/2510.20419v1

• NeuPerm: Disrupting Malware Hidden in Neural Network Parameters by
  Leveraging Permutation Symmetry
  http://arxiv.org/abs/2510.20367v1

• Classport: Designing Runtime Dependency Introspection for Java
  http://arxiv.org/abs/2510.20340v1

• GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in
  Dynamic On-Device Environments?
  http://arxiv.org/abs/2510.20333v1

• Enhancing Security in Deep Reinforcement Learning: A Comprehensive
  Survey on Adversarial Attacks and Defenses
  http://arxiv.org/abs/2510.20314v1

• Privacy Protection of Automotive Location Data Based on
  Format-Preserving Encryption of Geographical Coordinates
  http://arxiv.org/abs/2510.20300v1

• In-DRAM True Random Number Generation Using Simultaneous Multiple-Row
  Activation: An Experimental Study of Real DRAM Chips
  http://arxiv.org/abs/2510.20269v1

• HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine
  Learning on Edge
  http://arxiv.org/abs/2510.20243v1

• Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models
  through Perceptually Simple Transformations
  http://arxiv.org/abs/2510.20223v1

• Separating Pseudorandom Generators from Logarithmic Pseudorandom States
  http://arxiv.org/abs/2510.20131v1

• SAID: Empowering Large Language Models with Self-Activating Internal
  Defense
  http://arxiv.org/abs/2510.20129v1

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。