The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness

Ähnliche Einträge

• The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks
  von: Feng, Zhou, et al.
  Veröffentlicht: (2025)
• Hijack Vertical Federated Learning Models As One Party
  von: Qiu, Pengyu, et al.
  Veröffentlicht: (2022)
• CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
  von: Zeng, Rui, et al.
  Veröffentlicht: (2024)
• UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
  von: Ma, Oubo, et al.
  Veröffentlicht: (2025)
• Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
  von: Li, Qinglun, et al.
  Veröffentlicht: (2024)