TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Documenti analoghi

• Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
  di: Green, Tommaso, et al.
  Pubblicazione: (2025)
• Calibrating Large Language Models Using Their Generations Only
  di: Ulmer, Dennis, et al.
  Pubblicazione: (2024)
• LLM in the Shell: Generative Honeypots
  di: Sladić, Muris, et al.
  Pubblicazione: (2023)
• Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  di: Puerto, Haritz, et al.
  Pubblicazione: (2024)
• "Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
  di: Wang, Libo
  Pubblicazione: (2024)