Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

Documenti analoghi

• SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
  di: Xue, Eric, et al.
  Pubblicazione: (2025)
• A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
  di: Li, Ziqiang, et al.
  Pubblicazione: (2023)
• Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
  di: Li, Ziqiang, et al.
  Pubblicazione: (2023)
• Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
  di: Cao, Yuanpu, et al.
  Pubblicazione: (2023)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
  di: Yin, Rui, et al.
  Pubblicazione: (2026)