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

Documenti analoghi

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