Description

本日紹介した論文の一覧

• LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
  http://arxiv.org/abs/2408.03909v1

• Speech privacy-preserving methods using secret key for convolutional
  neural network models and their robustness evaluation
  http://arxiv.org/abs/2408.03897v1

• MTDSense: AI-Based Fingerprinting of Moving Target Defense Techniques in
  Software-Defined Networking
  http://arxiv.org/abs/2408.03758v1

• Limitations of the decoding-to-LPN reduction via code smoothing
  http://arxiv.org/abs/2408.03742v1

• Centralized Defense: Logging and Mitigation of Kubernetes
  Misconfigurations with Open Source Tools
  http://arxiv.org/abs/2408.03714v1

• BioDeepHash: Mapping Biometrics into a Stable Code
  http://arxiv.org/abs/2408.03704v1

• EnJa: Ensemble Jailbreak on Large Language Models
  http://arxiv.org/abs/2408.03603v1

• Unraveling Privacy Threat Modeling Complexity: Conceptual Privacy
  Analysis Layers
  http://arxiv.org/abs/2408.03578v1

• MPC-Minimized Secure LLM Inference
  http://arxiv.org/abs/2408.03561v1

• Empirical Analysis of Large Vision-Language Models against Goal
  Hijacking via Visual Prompt Injection
  http://arxiv.org/abs/2408.03554v1

• Harnessing the Power of LLMs in Source Code Vulnerability Detection
  http://arxiv.org/abs/2408.03489v1

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。