BadActs: A Universal Backdoor Defense in the Activation Space

Documenti analoghi

• Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
  di: Yi, Biao, et al.
  Pubblicazione: (2025)
• CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
  di: Yi, Biao, et al.
  Pubblicazione: (2025)
• BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
  di: Wang, Zihan, et al.
  Pubblicazione: (2025)
• BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
  di: Tong, Terry, et al.
  Pubblicazione: (2025)
• BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
  di: Wu, Zhengxian, et al.
  Pubblicazione: (2025)