Description

本日紹介した論文の一覧

• Differentially Private Space-Efficient Algorithms for Counting Distinct
  Elements in the Turnstile Model
  http://arxiv.org/abs/2505.23682v1

• Bayesian Perspective on Memorization and Reconstruction
  http://arxiv.org/abs/2505.23658v1

• Keyed Chaotic Tensor Transformations for Secure And Attributable Neural
  Inference
  http://arxiv.org/abs/2505.23655v1

• Securing AI Agents with Information-Flow Control
  http://arxiv.org/abs/2505.23643v1

• MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits
  using Improved Preference Alignment
  http://arxiv.org/abs/2505.23634v1

• Towards A Global Quantum Internet: A Review of Challenges Facing Aerial
  Quantum Networks
  http://arxiv.org/abs/2505.23603v1

• Quantum Hilbert Transform
  http://arxiv.org/abs/2505.23581v1

• Merge Hijacking: Backdoor Attacks to Model Merging of Large Language
  Models
  http://arxiv.org/abs/2505.23561v1

• A Unified Framework for Human AI Collaboration in Security Operations
  Centers with Trusted Autonomy
  http://arxiv.org/abs/2505.23397v1

• Joint Data Hiding and Partial Encryption of Compressive Sensed Streams
  http://arxiv.org/abs/2505.23357v1

• Disrupting Vision-Language Model-Driven Navigation Services via
  Adversarial Object Fusion
  http://arxiv.org/abs/2505.23266v1

• Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt
  Attacks
  http://arxiv.org/abs/2505.23192v1

• AgentAlign: Navigating Safety Alignment in the Shift from Informative to
  Agentic Large Language Models
  http://arxiv.org/abs/2505.23020v1

• Chainless Apps: A Modular Framework for Building Apps with Web2
  Capability and Web3 Trust
  http://arxiv.org/abs/2505.22989v1

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。