TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models

Documenti analoghi

• HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
  di: Liu, Han, et al.
  Pubblicazione: (2024)
• SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
  di: Liu, Han, et al.
  Pubblicazione: (2026)
• AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models
  di: Shu, Dong, et al.
  Pubblicazione: (2024)
• Jailbreaking Large Language Models with Morality Attacks
  di: Su, Ying, et al.
  Pubblicazione: (2026)
• Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
  di: Sun, Xiaobing, et al.
  Pubblicazione: (2026)