paper-with-me

홈 › Papers

Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling

2026-04-06 · Qingyang Xu, Yaling Shen, Stephanie Fong, Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Jiahe Liu, Zhongxing Xu, Vincent Lee, Zongyuan Ge arxiv

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive responses may inadvertently reinforce harmful beliefs or behaviors in multi-turn conversations. This risk is largely overlooked by existing red-teaming frameworks, which focus mainly on generic harms or optimization-based attacks. To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose vulnerabilities in psychological safety alignment. Experiments on seven general and mental health-specialized LLMs show that PCSA substantially outperforms four competitive baselines. Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues. Our results reveal that current LLMs remain vulnerable to domain-specific adversarial tactics, providing unauthorized medical advice, reinforcing delusions, and implicitly encouraging risky actions.

📄 PDF Abstract BibTeX arXiv:2604.04842

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests

2025-10-06 · Punya Syon Pandey, Hai Son Le, Devansh Bhardwaj, Rada Mihalcea 외 arxiv

Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as politica…

MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities

2026-08-26 · Tianshi Wang, Jingsong Wang, Yafei Huang, Fengling Li 외 arxiv

Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly understood. Existing benchmarks often couple h…

Enhancing Jailbreak Attacks on LLMs via Persona Prompts

2025-07-28 · Zheng Zhang, Peilin Zhao, Deheng Ye, Hao Wang arxiv

Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the…

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

2025-01-05 · Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua 외

As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However…

ChatbotCode Generation

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

2025-07-15 · Zichen Wen, Jiashu Qu, Dongrui Liu, Zhiyuan Liu 외

Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parallel decoding and bidirectional modeling. …

Code GenerationSafety AlignmentText GenerationText Infilling