Description

本日紹介した論文の一覧

• ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
  http://arxiv.org/abs/2506.10960v1

• Monitoring Decomposition Attacks in LLMs with Lightweight Sequential
  Monitors
  http://arxiv.org/abs/2506.10949v1

• ME: Trigger Element Combination Backdoor Attack on Copyright
  Infringement
  http://arxiv.org/abs/2506.10776v1

• Quantifying Azure RBAC Wildcard Overreach
  http://arxiv.org/abs/2506.10755v1

• ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types
  of Bit-Flip Attacks
  http://arxiv.org/abs/2506.10744v1

• TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
  http://arxiv.org/abs/2506.10722v1

• Commitment Schemes for Multi-Party Computation
  http://arxiv.org/abs/2506.10721v1

• Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework
  http://arxiv.org/abs/2506.10685v1

• GOLIATH: A Decentralized Framework for Data Collection in Intelligent
  Transportation Systems
  http://arxiv.org/abs/2506.10665v1

• From IOCs to Group Profiles: On the Specificity of Threat Group
  Behaviors in CTI Knowledge Bases
  http://arxiv.org/abs/2506.10645v1

• CyFence: Securing Cyber-Physical Controllers via Trusted Execution
  Environment
  http://arxiv.org/abs/2506.10638v1

• Assessing the Resilience of Automotive Intrusion Detection Systems to
  Adversarial Manipulation
  http://arxiv.org/abs/2506.10620v1

• SoK: Evaluating Jailbreak Guardrails for Large Language Models
  http://arxiv.org/abs/2506.10597v1

• A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring
  Watermarks
  http://arxiv.org/abs/2506.10502v1

• Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and
  Cybersecurity Applications
  http://arxiv.org/abs/2506.10467v1

• SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against
  Membership Inference Attacks
  http://arxiv.org/abs/2506.10424v1

• FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular
  Graph Convolutional Networks
  http://arxiv.org/abs/2506.10399v1

• Can We Infer Confidential Properties of Training Data from LLMs?
  http://arxiv.org/abs/2506.10364v1

• Adaptive Chosen-Ciphertext Security of Distributed Broadcast Encryption
  http://arxiv.org/abs/2506.10338v1

• A Comprehensive Survey of Unmanned Aerial Systems' Risks and Mitigation
  Strategies
  http://arxiv.org/abs/2506.10327v1

• ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer
  Space
  http://arxiv.org/abs/2506.10323v1

• AI-Based Software Vulnerability Detection: A Systematic Literature
  Review
  http://arxiv.org/abs/2506.10280v1

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。