A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning

Documenti analoghi

• DarkFed: A Data-Free Backdoor Attack in Federated Learning
  di: Li, Minghui, et al.
  Pubblicazione: (2024)
• GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning
  di: Gan, Xiaoyun, et al.
  Pubblicazione: (2024)
• PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systems
  di: Sun, Wei, et al.
  Pubblicazione: (2026)
• PPFPL: Cross-silo Privacy-preserving Federated Prototype Learning Against Data Poisoning Attacks
  di: Zhang, Hongliang, et al.
  Pubblicazione: (2025)
• Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
  di: Xu, Jiahao, et al.
  Pubblicazione: (2025)