Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting

Documenti analoghi

• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
  di: Yuan, Hongbang, et al.
  Pubblicazione: (2024)
• PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
  di: Pham, Viet, et al.
  Pubblicazione: (2025)
• Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach
  di: Sternak, Tvrtko, et al.
  Pubblicazione: (2025)
• AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
  di: Reddy, Aashray, et al.
  Pubblicazione: (2025)
• Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
  di: Zheng, Yujia, et al.
  Pubblicazione: (2025)