Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

Documenti analoghi

• A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks
  di: Li, Haoyang, et al.
  Pubblicazione: (2025)
• Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
  di: Liang, Zi, et al.
  Pubblicazione: (2024)
• MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
  di: Zhang, Xinwei, et al.
  Pubblicazione: (2025)
• Performance-lossless Black-box Model Watermarking
  di: Zhao, Na, et al.
  Pubblicazione: (2023)
• Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
  di: Liang, Zi, et al.
  Pubblicazione: (2025)