Description

本日紹介した論文の一覧

• AI-Driven Post-Quantum Cryptography for Cyber-Resilient V2X
  Communication in Transportation Cyber-Physical Systems
  http://arxiv.org/abs/2510.08496v1

• Compiling Any $\mathsf{MIP}^{*}$ into a (Succinct) Classical Interactive
  Argument
  http://arxiv.org/abs/2510.08495v1

• Rethinking Provenance Completeness with a Learning-Based Linux Scheduler
  http://arxiv.org/abs/2510.08479v1

• An Improved Quantum Algorithm for 3-Tuple Lattice Sieving
  http://arxiv.org/abs/2510.08473v1

• Parallel Spooky Pebbling Makes Regev Factoring More Practical
  http://arxiv.org/abs/2510.08432v1

• ExPrESSO: Zero-Knowledge backed Extensive Privacy Preserving Single
  Sign-on
  http://arxiv.org/abs/2510.08355v1

• A Haskell to FHE Transpiler
  http://arxiv.org/abs/2510.08343v1

• New Machine Learning Approaches for Intrusion Detection in ADS-B
  http://arxiv.org/abs/2510.08333v1

• Systematic Assessment of Cache Timing Vulnerabilities on RISC-V
  Processors
  http://arxiv.org/abs/2510.08272v1

• TracE2E: Easily Deployable Middleware for Decentralized Data
  Traceability
  http://arxiv.org/abs/2510.08225v1

• LLMs Learn to Deceive Unintentionally: Emergent Misalignment in
  Dishonesty from Misaligned Samples to Biased Human-AI Interactions
  http://arxiv.org/abs/2510.08211v1

• LLM-Assisted Web Measurements
  http://arxiv.org/abs/2510.08101v1

• A Novel Ensemble Learning Approach for Enhanced IoT Attack Detection:
  Redefining Security Paradigms in Connected Systems
  http://arxiv.org/abs/2510.08084v1

• A Unified Approach to Quantum Key Leasing with a Classical Lessor
  http://arxiv.org/abs/2510.08079v1

• Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and
  Defenses
  http://arxiv.org/abs/2510.08016v1

• Composition Law of Conjugate Observables in Random Permutation Sorting
  Systems
  http://arxiv.org/abs/2510.08013v1

• Fewer Weights, More Problems: A Practical Attack on LLM Pruning
  http://arxiv.org/abs/2510.07985v1

• From Defender to Devil? Unintended Risk Interactions Induced by LLM
  Defenses
  http://arxiv.org/abs/2510.07968v1

• Decentralised Blockchain Management Through Digital Twins
  http://arxiv.org/abs/2510.07901v1

• MetaDefense: Defending Finetuning-based Jailbreak Attack Before and
  During Generation
  http://arxiv.org/abs/2510.07835v1

• Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile
  Vision-Language Agents
  http://arxiv.org/abs/2510.07809v1

• ANCORA: Accurate Intrusion Recovery for Web Applications
  http://arxiv.org/abs/2510.07806v1

• Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
  http://arxiv.org/abs/2510.07697v1

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。