Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks

Documenti analoghi

• Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
  di: Pu, Rui, et al.
  Pubblicazione: (2025)
• Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
  di: Lei, Runlin, et al.
  Pubblicazione: (2024)
• Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
  di: Akbar-Tajari, Mohammad, et al.
  Pubblicazione: (2025)
• Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
  di: Gohil, Vasudev
  Pubblicazione: (2025)
• HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
  di: Liu, Han, et al.
  Pubblicazione: (2024)