Description

本日紹介した論文の一覧

• PacketCLIP: Multi-Modal Embedding of Network Traffic and Language for
  Cybersecurity Reasoning
  http://arxiv.org/abs/2503.03747v1

• Improving LLM Safety Alignment with Dual-Objective Optimization
  http://arxiv.org/abs/2503.03710v1

• Towards Trustworthy Federated Learning
  http://arxiv.org/abs/2503.03684v1

• Token-Level Privacy in Large Language Models
  http://arxiv.org/abs/2503.03652v1

• Benchmarking LLMs and LLM-based Agents in Practical Vulnerability
  Detection for Code Repositories
  http://arxiv.org/abs/2503.03586v1

• Data Sharing, Privacy and Security Considerations in the Energy Sector:
  A Review from Technical Landscape to Regulatory Specifications
  http://arxiv.org/abs/2503.03539v1

• Oblivious Digital Tokens
  http://arxiv.org/abs/2503.03494v1

• Differentially Private Learners for Heterogeneous Treatment Effects
  http://arxiv.org/abs/2503.03486v1

• Data Poisoning Attacks to Locally Differentially Private Range Query
  Protocols
  http://arxiv.org/abs/2503.03454v1

• Time-bin Phase and Polarization based QKD systems performance analysis
  over 16Km Aerial Fibers
  http://arxiv.org/abs/2503.03436v1

• Privacy is All You Need: Revolutionizing Wearable Health Data with
  Advanced PETs
  http://arxiv.org/abs/2503.03428v1

• Reduced Spatial Dependency for More General Video-level Deepfake
  Detection
  http://arxiv.org/abs/2503.03270v1

• Quantum-Inspired Privacy-Preserving Federated Learning Framework for
  Secure Dementia Classification
  http://arxiv.org/abs/2503.03267v1

• Less is more? Rewards in RL for Cyber Defence
  http://arxiv.org/abs/2503.03245v1

• Enhancing Cybersecurity in Critical Infrastructure with LLM-Assisted
  Explainable IoT Systems
  http://arxiv.org/abs/2503.03180v1

• AttackSeqBench: Benchmarking Large Language Models' Understanding of
  Sequential Patterns in Cyber Attacks
  http://arxiv.org/abs/2503.03170v1

• SpinML: Customized Synthetic Data Generation for Private Training of
  Specialized ML Models
  http://arxiv.org/abs/2503.03160v1

• PriFFT: Privacy-preserving Federated Fine-tuning of Large Language
  Models via Function Secret Sharing
  http://arxiv.org/abs/2503.03146v1

• SoK: Knowledge is All You Need: Last Mile Delivery for Automated
  Provenance-based Intrusion Detection with LLMs
  http://arxiv.org/abs/2503.03108v1

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。