Description

本日紹介した論文の一覧

• Unveiling Wireless Users' Locations via Modulation Classification-based
  Passive Attack
  http://arxiv.org/abs/2502.19341v1

• Shh, don't say that! Domain Certification in LLMs
  http://arxiv.org/abs/2502.19320v1

• Poster: Long PHP webshell files detection based on sliding window
  attention
  http://arxiv.org/abs/2502.19257v1

• Towards Privacy-Preserving Anomaly-Based Intrusion Detection in Energy
  Communities
  http://arxiv.org/abs/2502.19154v1

• XSS Adversarial Attacks Based on Deep Reinforcement Learning: A
  Replication and Extension Study
  http://arxiv.org/abs/2502.19095v1

• A Sample-Level Evaluation and Generative Framework for Model Inversion
  Attacks
  http://arxiv.org/abs/2502.19070v1

• Beyond Surface-Level Patterns: An Essence-Driven Defense Framework
  Against Jailbreak Attacks in LLMs
  http://arxiv.org/abs/2502.19041v1

• Evaluating Membership Inference Attacks in heterogeneous-data setups
  http://arxiv.org/abs/2502.18986v1

• Switching multiplicative watermark design against covert attacks
  http://arxiv.org/abs/2502.18948v1

• Towards Label-Only Membership Inference Attack against Pre-trained Large
  Language Models
  http://arxiv.org/abs/2502.18943v1

• Marking Code Without Breaking It: Code Watermarking for Detecting
  LLM-Generated Code
  http://arxiv.org/abs/2502.18851v1

• Adversarial Universal Stickers: Universal Perturbation Attacks on
  Traffic Sign using Stickers
  http://arxiv.org/abs/2502.18724v1

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。