FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning

Ähnliche Einträge

• SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
  von: Paracha, Anum, et al.
  Veröffentlicht: (2025)
• FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
  von: Han, Shanshan, et al.
  Veröffentlicht: (2023)
• ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
  von: Zhao, Haodong, et al.
  Veröffentlicht: (2026)
• A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning
  von: Yang, Yuxin, et al.
  Veröffentlicht: (2024)
• FedRecAttack: Model Poisoning Attack to Federated Recommendation
  von: Rong, Dazhong, et al.
  Veröffentlicht: (2022)