Description

本日紹介した論文の一覧

• PostMark: A Robust Blackbox Watermark for Large Language Models
  http://arxiv.org/abs/2406.14517v1

• Mind the Privacy Unit! User-Level Differential Privacy for Language
  Model Fine-Tuning
  http://arxiv.org/abs/2406.14322v1

• The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in
  Prompts
  http://arxiv.org/abs/2406.14318v1

• On countering adversarial perturbations in graphs using error correcting
  codes
  http://arxiv.org/abs/2406.14245v1

• Defending Against Sophisticated Poisoning Attacks with RL-based
  Aggregation in Federated Learning
  http://arxiv.org/abs/2406.14217v1

• Dye4AI: Assuring Data Boundary on Generative AI Services
  http://arxiv.org/abs/2406.14114v1

• SeCTIS: A Framework to Secure CTI Sharing
  http://arxiv.org/abs/2406.14102v1

• Leveraging eBPF and AI for Ransomware Nose Out
  http://arxiv.org/abs/2406.14020v1

• A note on cyclic non-MDS matrices
  http://arxiv.org/abs/2406.14013v1

• The Elusive Pursuit of Replicating PATE-GAN: Benchmarking, Auditing,
  Debugging
  http://arxiv.org/abs/2406.13985v1

• EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in
  Text-to-image Diffusion Models with Minimal and Robust Alterations
  http://arxiv.org/abs/2406.13933v1

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。