MEA-Defender: A Robust Watermark against Model Extraction Attack

Documenti analoghi

• SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
  di: Lv, Peizhuo, et al.
  Pubblicazione: (2022)
• LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
  di: Lv, Peizhuo, et al.
  Pubblicazione: (2025)
• A Model Stealing Attack Against Multi-Exit Networks
  di: Pan, Li, et al.
  Pubblicazione: (2023)
• ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
  di: Pang, Kaiyi, et al.
  Pubblicazione: (2024)
• RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
  di: Lv, Peizhuo, et al.
  Pubblicazione: (2025)