Backdoor Attack on Multilingual Machine Translation

Documenti analoghi

• SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
  di: He, Xuanli, et al.
  Pubblicazione: (2024)
• TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
  di: He, Xuanli, et al.
  Pubblicazione: (2024)
• Defending against Backdoor Attacks via Module Switching
  di: Li, Weijun, et al.
  Pubblicazione: (2025)
• Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
  di: Tong, Yao, et al.
  Pubblicazione: (2024)
• Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge
  di: Arora, Ansh, et al.
  Pubblicazione: (2024)