Enhancing Jailbreak Attacks on LLMs via Persona Prompts
Zhang, Zheng, Zhao, Peilin, Ye, Deheng, Wang, Hao
–arXiv.org Artificial Intelligence
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 field of LLM safety. Previous jailbreak approaches have mainly focused on direct manipulations of harmful intent, with limited attention to the impact of persona prompts. In this study, we systematically explore the efficacy of persona prompts in compromising LLM defenses. We propose a genetic algorithm-based method that automatically crafts persona prompts to bypass LLM's safety mechanisms. Our experiments reveal that: (1) our evolved persona prompts reduce refusal rates by 50-70% across multiple LLMs, and (2) these prompts demonstrate synergistic effects when combined with existing attack methods, increasing success rates by 10-20%. Our code and data are available at https://github.com/CjangCjengh/Generic_Persona.
arXiv.org Artificial Intelligence
Dec-2-2025
- Country:
- Asia
- China
- Guangdong Province > Guangzhou (0.04)
- Hong Kong (0.04)
- Indonesia > Bali (0.04)
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Singapore (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- China
- North America > United States
- Florida > Miami-Dade County > Miami (0.04)
- Asia
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Banking & Finance (1.00)
- Government > Military (0.68)
- Information Technology > Security & Privacy (1.00)
- Law Enforcement & Public Safety > Crime Prevention & Enforcement (0.67)
- Technology: