Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Abstract: The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as academic papers, implying new possible vulnerabilities. To verify this possibility, a preliminary analysis is designed to illustrate our two findings. Based on this insight, a novel jailbreaking method, Paper Summary Attack (PSA), is proposed. It systematically synthesizes content from either attack-focused or defense-focused LLM safety paper to construct an adversarial prompt template, while strategically infilling harmful query as adversarial payloads within predefined subsections. Extensive experiments show significant vulnerabilities not only in base LLMs, but also in state-of-the-art reasoning model like Deepseek-R1. PSA achieves a 97% attack success rate (ASR) on well-aligned models like Claude3.5-Sonnet and an even higher 98% ASR on Deepseek-R1. More intriguingly, our work has further revealed diametrically opposed vulnerability bias across different base models, and even between different versions of the same model, when exposed to either attack-focused or defense-focused papers. This phenomenon potentially indicates future research clues for both adversarial methodologies and safety alignment.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: Language Modeling，Interpretability and Analysis of Models for NLP
Contribution Types: Model analysis & interpretability, Data resources
Languages Studied: English
Submission Number: 6506
Loading