Схожие документы

• Hijacking Large Language Models via Adversarial In-Context Learning
  по: Zhou, Xiangyu, и др.
  Опубликовано: (2023)
• Not All Tokens Are Meant to Be Forgotten
  по: Zhou, Xiangyu, и др.
  Опубликовано: (2025)
• Automatic Calibration for Membership Inference Attack on Large Language Models
  по: Zade, Saleh Zare, и др.
  Опубликовано: (2025)
• Attention Smoothing Is All You Need For Unlearning
  по: Zade, Saleh Zare, и др.
  Опубликовано: (2026)
• Denial-of-Service Poisoning Attacks against Large Language Models
  по: Gao, Kuofeng, и др.
  Опубликовано: (2024)