Description

本日紹介した論文の一覧

• ARQ: A Mixed-Precision Quantization Framework for Accurate and
  Certifiably Robust DNNs
  http://arxiv.org/abs/2410.24214v1

• Untelegraphable Encryption and its Applications
  http://arxiv.org/abs/2410.24189v1

• Assessing the Impact of Packing on Machine Learning-Based Malware
  Detection and Classification Systems
  http://arxiv.org/abs/2410.24017v1

• Distributing Intelligence in 6G Programmable Data Planes for Effective
  In-Network Deployment of an Active Intrusion Detection System
  http://arxiv.org/abs/2410.24013v1

• Metamorphic Malware Evolution: The Potential and Peril of Large Language
  Models
  http://arxiv.org/abs/2410.23894v1

• Noise as a Double-Edged Sword: Reinforcement Learning Exploits
  Randomized Defenses in Neural Networks
  http://arxiv.org/abs/2410.23870v1

• Zero-shot Class Unlearning via Layer-wise Relevance Analysis and
  Neuronal Path Perturbation
  http://arxiv.org/abs/2410.23693v1

• Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
  http://arxiv.org/abs/2410.23687v1

• Across-Platform Detection of Malicious Cryptocurrency Transactions via
  Account Interaction Learning
  http://arxiv.org/abs/2410.23563v1

• Transferable Ensemble Black-box Jailbreak Attacks on Large Language
  Models
  http://arxiv.org/abs/2410.23558v1

• EVeCA: Efficient and Verifiable On-Chain Data Query Framework Using
  Challenge-Based Authentication
  http://arxiv.org/abs/2410.23546v1

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。