BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning

Documenti analoghi

• BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
  di: Duan, Kaiwen, et al.
  Pubblicazione: (2025)
• PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
  di: Liu, Yi, et al.
  Pubblicazione: (2025)
• SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  di: Zhang, Heyi, et al.
  Pubblicazione: (2025)
• Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts
  di: Liu, Yi, et al.
  Pubblicazione: (2024)
• Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity
  di: Zuo, Shiyuan, et al.
  Pubblicazione: (2024)