A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning

Documenti analoghi

• Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
  di: Yang, Yuxin, et al.
  Pubblicazione: (2024)
• Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
  di: Nie, Chenfei, et al.
  Pubblicazione: (2024)
• FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
  di: Yang, Yuxin, et al.
  Pubblicazione: (2024)
• Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
  di: Wang, Zifan, et al.
  Pubblicazione: (2024)
• Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
  di: Hong, Hanbin, et al.
  Pubblicazione: (2023)