Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Documenti analoghi

• Privacy in Large Language Models: Attacks, Defenses and Future Directions
  di: Li, Haoran, et al.
  Pubblicazione: (2023)
• BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
  di: Chen, Yulin, et al.
  Pubblicazione: (2024)
• PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
  di: Li, Haoran, et al.
  Pubblicazione: (2023)
• Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
  di: Chen, Yulin, et al.
  Pubblicazione: (2025)
• GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
  di: Fan, Wei, et al.
  Pubblicazione: (2024)