Description

本日紹介した論文の一覧

• Hessian-aware Training for Enhancing DNNs Resilience to Parameter
  Corruptions
  http://arxiv.org/abs/2504.01933v1

• Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs
  CPU-Based ML Libraries
  http://arxiv.org/abs/2504.01905v1

• Lower Bounds for Leader Election and Collective Coin Flipping, Revisited
  http://arxiv.org/abs/2504.01856v1

• DISINFOX: an open-source threat exchange platform serving intelligence
  on disinformation and influence operations
  http://arxiv.org/abs/2504.01803v1

• Vers une modélisation de la confiance dans le renseignement sur les
  menaces cyber
  http://arxiv.org/abs/2504.01606v1

• Representation Bending for Large Language Model Safety
  http://arxiv.org/abs/2504.01550v1

• LightDefense: A Lightweight Uncertainty-Driven Defense against
  Jailbreaks via Shifted Token Distribution
  http://arxiv.org/abs/2504.01533v1

• Identifying Obfuscated Code through Graph-Based Semantic Analysis of
  Binary Code
  http://arxiv.org/abs/2504.01481v1

• PiCo: Jailbreaking Multimodal Large Language Models via
  $\textbf{Pi}$ctorial $\textbf{Co}$de Contextualization
  http://arxiv.org/abs/2504.01444v1

• From Easy to Hard: Building a Shortcut for Differentially Private Image
  Synthesis
  http://arxiv.org/abs/2504.01395v1

• FireGuard: A Generalized Microarchitecture for Fine-Grained Security
  Analysis on OoO Superscalar Cores
  http://arxiv.org/abs/2504.01380v1

• A Novel Framework To Assess Cybersecurity Capability Maturity
  http://arxiv.org/abs/2504.01305v1

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。