Description

本日紹介した論文の一覧

• Evaluating Large Language Models for Phishing Detection,
  Self-Consistency, Faithfulness, and Explainability
  http://arxiv.org/abs/2506.13746v1

• ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
  http://arxiv.org/abs/2506.13737v1

• Weakest Link in the Chain: Security Vulnerabilities in Advanced
  Reasoning Models
  http://arxiv.org/abs/2506.13726v1

• EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated
  Learning
  http://arxiv.org/abs/2506.13612v1

• Agent Capability Negotiation and Binding Protocol (ACNBP)
  http://arxiv.org/abs/2506.13590v1

• Unlearning-Enhanced Website Fingerprinting Attack: Against Backdoor
  Poisoning in Anonymous Networks
  http://arxiv.org/abs/2506.13563v1

• Watermarking LLM-Generated Datasets in Downstream Tasks
  http://arxiv.org/abs/2506.13494v1

• From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in
  the Age of LLMs
  http://arxiv.org/abs/2506.13434v1

• New characterization of full weight spectrum one-orbit cyclic subspace
  codes
  http://arxiv.org/abs/2506.13418v1

• The Rich Get Richer in Bitcoin Mining Induced by Blockchain Forks
  http://arxiv.org/abs/2506.13360v1

• Tady: A Neural Disassembler without Structural Constraint Violations
  http://arxiv.org/abs/2506.13323v1

• Building Automotive Security on Internet Standards: An Integration of
  DNSSEC, DANE, and DANCE to Authenticate and Authorize In-Car Services
  http://arxiv.org/abs/2506.13261v1

• On Immutable Memory Systems for Artificial Agents: A Blockchain-Indexed
  Automata-Theoretic Framework Using ECDH-Keyed Merkle Chains
  http://arxiv.org/abs/2506.13246v1

• Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
  http://arxiv.org/abs/2506.13205v1

• Dual Protection Ring: User Profiling Via Differential Privacy and
  Service Dissemination Through Private Information Retrieval
  http://arxiv.org/abs/2506.13170v1

• Using LLMs for Security Advisory Investigations: How Far Are We?
  http://arxiv.org/abs/2506.13161v1

• CertDW: Towards Certified Dataset Ownership Verification via Conformal
  Prediction
  http://arxiv.org/abs/2506.13160v1

• Detecting Hard-Coded Credentials in Software Repositories via LLMs
  http://arxiv.org/abs/2506.13090v1

• Buy it Now, Track Me Later: Attacking User Privacy via Wi-Fi AP Online
  Auctions
  http://arxiv.org/abs/2506.13052v1

• Position: Certified Robustness Does Not (Yet) Imply Model Security
  http://arxiv.org/abs/2506.13024v1

• Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A
  New Inference Attack Perspective
  http://arxiv.org/abs/2506.13009v1

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。