Goal Hijacking Attack on Large Language Models via Pseudo-Conversation Injection

Documenti analoghi

• Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection
  di: Kimura, Subaru, et al.
  Pubblicazione: (2024)
• Goal-guided Generative Prompt Injection Attack on Large Language Models
  di: Zhang, Chong, et al.
  Pubblicazione: (2024)
• Hijacking Large Language Models via Adversarial In-Context Learning
  di: Zhou, Xiangyu, et al.
  Pubblicazione: (2023)
• J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain
  di: Hu, Yiran, et al.
  Pubblicazione: (2025)
• Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
  di: Zhang, Zhexin, et al.
  Pubblicazione: (2023)