SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs

Documenti analoghi

• BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation
  di: Wu, Zhengxian, 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)
• Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
  di: Fu, Hang, et al.
  Pubblicazione: (2026)
• Is Your Writing Being Mimicked by AI? Unveiling Imitation with Invisible Watermarks in Creative Writing
  di: Zhang, Ziwei, et al.
  Pubblicazione: (2025)
• Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion
  di: Zhou, Yinghan, et al.
  Pubblicazione: (2025)