NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models

Documenti analoghi

• EmbTracker: Traceable Black-box Watermarking for Federated Language Models
  di: Zhao, Haodong, et al.
  Pubblicazione: (2026)
• UOR: Universal Backdoor Attacks on Pre-trained Language Models
  di: Du, Wei, et al.
  Pubblicazione: (2023)
• Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
  di: Zhao, Haodong, et al.
  Pubblicazione: (2026)
• Transferring Backdoors between Large Language Models by Knowledge Distillation
  di: Cheng, Pengzhou, et al.
  Pubblicazione: (2024)
• Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
  di: Li, Fangqi, et al.
  Pubblicazione: (2024)