Description

本日紹介した論文の一覧

• Cutting through buggy adversarial example defenses: fixing 1 line of
  code breaks Sabre
  http://arxiv.org/abs/2405.03672v1

• Can LLMs Deeply Detect Complex Malicious Queries? A Framework for
  Jailbreaking via Obfuscating Intent
  http://arxiv.org/abs/2405.03654v1

• When LLMs Meet Cybersecurity: A Systematic Literature Review
  http://arxiv.org/abs/2405.03644v1

• Federated Learning Privacy: Attacks, Defenses, Applications, and Policy
  Landscape - A Survey
  http://arxiv.org/abs/2405.03636v1

• LaserEscape: Detecting and Mitigating Optical Probing Attacks
  http://arxiv.org/abs/2405.03632v1

• Detecting Android Malware: From Neural Embeddings to Hands-On Validation
  with BERTroid
  http://arxiv.org/abs/2405.03620v1

• A Formal Model of Security Controls' Capabilities and Its Applications
  to Policy Refinement and Incident Management
  http://arxiv.org/abs/2405.03544v1

• QBER: Quantifying Cyber Risks for Strategic Decisions
  http://arxiv.org/abs/2405.03513v1

• UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and
  AI-Generated Images
  http://arxiv.org/abs/2405.03486v1

• Synthetic Datasets for Program Similarity Research
  http://arxiv.org/abs/2405.03478v1

• SEvenLLM: Benchmarking, Eliciting, and Enhancing Abilities of Large
  Language Models in Cyber Threat Intelligence
  http://arxiv.org/abs/2405.03446v1

• Provably Unlearnable Examples
  http://arxiv.org/abs/2405.03316v1

• DarkFed: A Data-Free Backdoor Attack in Federated Learning
  http://arxiv.org/abs/2405.03299v1

• Online Clustering of Known and Emerging Malware Families
  http://arxiv.org/abs/2405.03298v1

• PCG: Mitigating Conflict-based Cache Side-channel Attacks with
  Prefetching
  http://arxiv.org/abs/2405.03217v1

• Impact of EIP-4844 on Ethereum: Consensus Security, Ethereum Usage,
  Rollup Transaction Dynamics, and Blob Gas Fee Markets
  http://arxiv.org/abs/2405.03183v1

• An Efficient All-to-All GCD Algorithm for Low Entropy RSA Key
  Factorization
  http://arxiv.org/abs/2405.03166v1

• FOBNN: Fast Oblivious Binarized Neural Network Inference
  http://arxiv.org/abs/2405.03136v1

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。