Description

本日紹介した論文の一覧

• Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
  http://arxiv.org/abs/2509.18058v1

• Hybrid Reputation Aggregation: A Robust Defense Mechanism for
  Adversarial Federated Learning in 5G and Edge Network Environments
  http://arxiv.org/abs/2509.18044v1

• STAFF: Stateful Taint-Assisted Full-system Firmware Fuzzing
  http://arxiv.org/abs/2509.18039v1

• Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data
  Synthesis
  http://arxiv.org/abs/2509.18014v1

• The Reverse File System: Towards open cost-effective secure WORM storage
  devices for logging
  http://arxiv.org/abs/2509.17969v1

• What if we could hot swap our Biometrics?
  http://arxiv.org/abs/2509.17962v1

• B-Privacy: Defining and Enforcing Privacy in Weighted Voting
  http://arxiv.org/abs/2509.17871v1

• Federated Learning in the Wild: A Comparative Study for Cybersecurity
  under Non-IID and Unbalanced Settings
  http://arxiv.org/abs/2509.17836v1

• AEAS: Actionable Exploit Assessment System
  http://arxiv.org/abs/2509.17832v1

• Quickest Change Detection in Continuous-Time in Presence of a Covert
  Adversary
  http://arxiv.org/abs/2509.17778v1

• Public Key Encryption with Equality Test from Tag-Based Encryption
  http://arxiv.org/abs/2509.17722v1

• Ordered Multi-Signatures with Public-Key Aggregation from SXDH
  Assumption
  http://arxiv.org/abs/2509.17709v1

• Impossibility Results of Card-Based Protocols via Mathematical
  Optimization
  http://arxiv.org/abs/2509.17595v1

• PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera
  Identification
  http://arxiv.org/abs/2509.17581v1

• Community Covert Communication - Dynamic Mass Covert Communication
  Through Social Media
  http://arxiv.org/abs/2509.17508v1

• Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation
  for LLM-Powered Agents
  http://arxiv.org/abs/2509.17488v1

• DINVMark: A Deep Invertible Network for Video Watermarking
  http://arxiv.org/abs/2509.17416v1

• A Lightweight Authentication and Key Agreement Protocol Design for FANET
  http://arxiv.org/abs/2509.17409v1

• SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
  http://arxiv.org/abs/2509.17371v1

• TextCrafter: Optimization-Calibrated Noise for Defending Against Text
  Embedding Inversion
  http://arxiv.org/abs/2509.17302v1

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。