Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models

Documenti analoghi

• UOR: Universal Backdoor Attacks on Pre-trained Language Models
  di: Du, Wei, et al.
  Pubblicazione: (2023)
• Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency
  di: Wang, Bingzheng, et al.
  Pubblicazione: (2026)
• Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
  di: Kong, Cong, et al.
  Pubblicazione: (2024)
• Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
  di: Fu, Anmin, et al.
  Pubblicazione: (2025)
• Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
  di: Li, Xi, et al.
  Pubblicazione: (2024)