Description

本日紹介した論文の一覧

• Learning Pseudorandom Numbers with Transformers: Permuted Congruential
  Generators, Curricula, and Interpretability
  http://arxiv.org/abs/2510.26792v1

• Toward Automated Security Risk Detection in Large Software Using Call
  Graph Analysis
  http://arxiv.org/abs/2510.26620v1

• A DRL-Empowered Multi-Level Jamming Approach for Secure Semantic
  Communication
  http://arxiv.org/abs/2510.26610v1

• A Comprehensive Evaluation and Practice of System Penetration Testing
  http://arxiv.org/abs/2510.26555v1

• Interdependent Privacy in Smart Homes: Hunting for Bystanders in Privacy
  Policies
  http://arxiv.org/abs/2510.26523v1

• CyberNER: A Harmonized STIX Corpus for Cybersecurity Named Entity
  Recognition
  http://arxiv.org/abs/2510.26499v1

• SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset
  Ownership Verification
  http://arxiv.org/abs/2510.26420v1

• A Survey of Heterogeneous Graph Neural Networks for Cybersecurity
  Anomaly Detection
  http://arxiv.org/abs/2510.26307v1

• PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
  http://arxiv.org/abs/2510.26274v1

• Who Grants the Agent Power? Defending Against Instruction Injection via
  Task-Centric Access Control
  http://arxiv.org/abs/2510.26212v1

• Who Moved My Transaction? Uncovering Post-Transaction Auditability
  Vulnerabilities in Modern Super Apps
  http://arxiv.org/abs/2510.26210v1

• Confidential FRIT via Homomorphic Encryption
  http://arxiv.org/abs/2510.26179v1

• Security Risk of Misalignment between Text and Image in Multi-modal
  Model
  http://arxiv.org/abs/2510.26105v1

• Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of
  Public GitHub Repositories
  http://arxiv.org/abs/2510.26103v1

• PEEL: A Poisoning-Exposing Encoding Theoretical Framework for Local
  Differential Privacy
  http://arxiv.org/abs/2510.26102v1

• ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for
  Audio-Language Models
  http://arxiv.org/abs/2510.26096v1

• SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled
  Structured Reasoning
  http://arxiv.org/abs/2510.26037v1

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。