The Great Pretender: A Stochasticity Problem in LLM Jailbreak

ArXi:2605.14418v1 Announce Type: cross "Oh-Oh, yes, I'm the great pretender. Pretending that I'm doing well. My need is such, I pretend too much. " summarizes the state in the area of jailbreak creation and evaluation. You find this method to generate adversarial attacks proposed by a reputable institution (e.g., BoN from Anthropic or Crescendo from Microsoft Research). However, this method does not deliver on the promise claimed in the paper despite having top ASR scores against industry-grade LLMs. You successfully generate the jailbreak prompts against your target (open) model.