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

Documenti analoghi

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