Description

本日紹介した論文の一覧

• Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large
  Language Models?
  http://arxiv.org/abs/2408.02651v1

• Detection of Compromised Functions in a Serverless Cloud Environment
  http://arxiv.org/abs/2408.02641v1

• Command-line Obfuscation Detection using Small Language Models
  http://arxiv.org/abs/2408.02637v1

• Introducing a Comprehensive, Continuous, and Collaborative Survey of
  Intrusion Detection Datasets
  http://arxiv.org/abs/2408.02521v1

• Practical Attacks against Black-box Code Completion Engines
  http://arxiv.org/abs/2408.02509v1

• Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in
  Customized Large Language Models
  http://arxiv.org/abs/2408.02416v1

• From Generalist to Specialist: Exploring CWE-Specific Vulnerability
  Detection
  http://arxiv.org/abs/2408.02329v1

• XDC Network Assessment: Decentralization, Scalability and Security
  http://arxiv.org/abs/2408.02318v1

• Quantum Clustering for Cybersecurity
  http://arxiv.org/abs/2408.02314v1

• A Lean Transformer Model for Dynamic Malware Analysis and Detection
  http://arxiv.org/abs/2408.02313v1

• On the Robustness of Malware Detectors to Adversarial Samples
  http://arxiv.org/abs/2408.02310v1

• PROF: Protected Order Flow in a Profit-Seeking World
  http://arxiv.org/abs/2408.02303v1

• SoK: Fighting Counterfeits with Cyber-Physical Synergy Based on
  Physically-Unclonable Identifiers of Paper Surface
  http://arxiv.org/abs/2408.02221v1

• X.509 Information Security Certification Based on Post-Quantum
  Cryptography
  http://arxiv.org/abs/2408.02179v1

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。