Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

Documenti analoghi

• Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
  di: Zhao, Shuai, et al.
  Pubblicazione: (2024)
• Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
  di: Zhao, Shuai, et al.
  Pubblicazione: (2024)
• A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
  di: Zhao, Shuai, et al.
  Pubblicazione: (2024)
• P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
  di: Zhao, Shuai, et al.
  Pubblicazione: (2025)
• Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
  di: Zhao, Shuai, et al.
  Pubblicazione: (2024)