Watermark Smoothing Attacks against Language Models

Documenti analoghi

• Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
  di: Chang, Hongyan, et al.
  Pubblicazione: (2024)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
  di: Robey, Alexander, et al.
  Pubblicazione: (2023)
• Watermarking Language Models with Error Correcting Codes
  di: Chao, Patrick, et al.
  Pubblicazione: (2024)
• Range Membership Inference Attacks
  di: Tao, Jiashu, et al.
  Pubblicazione: (2024)
• Low-Cost High-Power Membership Inference Attacks
  di: Zarifzadeh, Sajjad, et al.
  Pubblicazione: (2023)