Description

本日紹介した論文の一覧

• Smart Contract Intent Detection with Pre-trained Programming Language
  Model
  http://arxiv.org/abs/2508.20086v1

• Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy
  Retriever Poisoning
  http://arxiv.org/abs/2508.20083v1

• SCAMPER -- Synchrophasor Covert chAnnel for Malicious and Protective
  ERrands
  http://arxiv.org/abs/2508.20051v1

• SoK: Large Language Model Copyright Auditing via Fingerprinting
  http://arxiv.org/abs/2508.19843v1

• Every Keystroke You Make: A Tech-Law Measurement and Analysis of Event
  Listeners for Wiretapping
  http://arxiv.org/abs/2508.19825v1

• From Research to Reality: Feasibility of Gradient Inversion Attacks in
  Federated Learning
  http://arxiv.org/abs/2508.19819v1

• The Art of Hide and Seek: Making Pickle-Based Model Supply Chain
  Poisoning Stealthy Again
  http://arxiv.org/abs/2508.19774v1

• Addressing Deepfake Issue in Selfie banking through camera based
  authentication
  http://arxiv.org/abs/2508.19714v1

• Safety Alignment Should Be Made More Than Just A Few Attention Heads
  http://arxiv.org/abs/2508.19697v1

• Intellectual Property in Graph-Based Machine Learning as a Service:
  Attacks and Defenses
  http://arxiv.org/abs/2508.19641v1

• A Scenario-Oriented Survey of Federated Recommender Systems: Techniques,
  Challenges, and Future Directions
  http://arxiv.org/abs/2508.19620v1

• Breaking the Layer Barrier: Remodeling Private Transformer Inference
  with Hybrid CKKS and MPC
  http://arxiv.org/abs/2508.19525v1

• Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H)
  Agent Unlocks Adversarial Skills
  http://arxiv.org/abs/2508.19500v1

• Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered
  Smartphone Agents
  http://arxiv.org/abs/2508.19493v1

• PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for
  Cyber Defense
  http://arxiv.org/abs/2508.19488v1

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。