Description

本日紹介した論文の一覧

• A Review of Privacy Metrics for Privacy-Preserving Synthetic Data
  Generation
  http://arxiv.org/abs/2507.11324v1

• LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence
  Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
  http://arxiv.org/abs/2507.11310v1

• Bridging the Gap in Vision Language Models in Identifying Unsafe
  Concepts Across Modalities
  http://arxiv.org/abs/2507.11155v1

• FacialMotionID: Identifying Users of Mixed Reality Headsets using
  Abstract Facial Motion Representations
  http://arxiv.org/abs/2507.11138v1

• Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks
  in Weight-based Neural Network Watermarking
  http://arxiv.org/abs/2507.11137v1

• Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
  http://arxiv.org/abs/2507.11112v1

• Security Enclave Architecture for Heterogeneous Security Primitives for
  Supply-Chain Attacks
  http://arxiv.org/abs/2507.10971v1

• DVFS: A Dynamic Verifiable Fuzzy Search Service for Encrypted Cloud Data
  http://arxiv.org/abs/2507.10927v1

• MalCodeAI: Autonomous Vulnerability Detection and Remediation via
  Language Agnostic Code Reasoning
  http://arxiv.org/abs/2507.10898v1

• From Alerts to Intelligence: A Novel LLM-Aided Framework for Host-based
  Intrusion Detection
  http://arxiv.org/abs/2507.10873v1

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。