BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning

Abstract

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed example. By expanding each step upon the model's previous responses, BAIT turns the model's own reasoning and consistency tendency into a disclosure pathway. Experiments on AdvBench, JailbreakBench, AIR-Ben

Categories

Framework mappings

Suggested from the entry's categories.

@misc{luo2026bait,
  title = {{BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning}},
  author = {Xuan Luo and Yue Wang and Geng Tu and Jing Li and Ruifeng Xu},
  year = {2026},
  month = may,
  eprint = {2605.27110},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.27110}
}