MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety

Abstract

Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke authority. We introduce MultiTurnPSB, a four-turn adversarial extension of PatientSafetyBench, and evaluate GPT-4.1-mini under fixed template, template-adaptive, and live adversarial attacks. Unsafe responses rise from 35% to nearly 80% by Turn 4 under live attack. Under the same adversary, GPT-4.1-mini and Claude Sonnet 4.5 are statistically indistingui

Categories

Framework mappings

Suggested from the entry's categories.

@misc{sheoran2026multiturnpsb,
  title = {{MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety}},
  author = {Anushka Sheoran and Yiduo Hao},
  year = {2026},
  month = may,
  eprint = {2606.02630},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.02630}
}