DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing

Abstract

As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical problem. Existing defenses often rely on known-attack coverage, prompt-level semantic judgment, or local runtime control, yet these paths can become unstable under evolving prompt packaging, expression rewriting, and structure manipulation. We observe that many black-box jailbreaks do not remove the harmful goal, but reorganize the information needed to

Categories

Framework mappings

Suggested from the entry's categories.

@misc{yin2026doubtprobe,
  title = {{DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing}},
  author = {Xuanyu Yin and Yilin Jiang and Jun Zhou and Kai Chen and Zhengfu Cao and Xiaolei Dong},
  year = {2026},
  month = jun,
  eprint = {2606.16527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.16527}
}