"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks

Ähnliche Einträge

• FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
  von: Gong, Yichen, et al.
  Veröffentlicht: (2023)
• Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
  von: Akbar-Tajari, Mohammad, et al.
  Veröffentlicht: (2025)
• Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
  von: Gohil, Vasudev
  Veröffentlicht: (2025)
• Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
  von: Tu, Shangqing, et al.
  Veröffentlicht: (2024)
• Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
  von: Mehrotra, Anay, et al.
  Veröffentlicht: (2023)