Hijacking Large Language Models via Adversarial In-Context Learning

Documenti analoghi

• Learning to Poison Large Language Models for Downstream Manipulation
  di: Zhou, Xiangyu, et al.
  Pubblicazione: (2024)
• Automatic Calibration for Membership Inference Attack on Large Language Models
  di: Zade, Saleh Zare, et al.
  Pubblicazione: (2025)
• Not All Tokens Are Meant to Be Forgotten
  di: Zhou, Xiangyu, et al.
  Pubblicazione: (2025)
• Image Hijacks: Adversarial Images can Control Generative Models at Runtime
  di: Bailey, Luke, et al.
  Pubblicazione: (2023)
• Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection
  di: Kimura, Subaru, et al.
  Pubblicazione: (2024)