Xuehai Tang

Liang Lin, Zhihao Xu, Xuehai Tang et al.

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 (\llmname{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.Code is available at https://github.com/233liang/Paper-Summary-Attack

Xikang Yang, Xuehai Tang, Songlin Hu et al.

Large language models (LLMs) have achieved remarkable performance in various natural language processing tasks, especially in dialogue systems. However, LLM may also pose security and moral threats, especially in multi round conversations where large models are more easily guided by contextual content, resulting in harmful or biased responses. In this paper, we present a novel method to attack LLMs in multi-turn dialogues, called CoA (Chain of Attack). CoA is a semantic-driven contextual multi-turn attack method that adaptively adjusts the attack policy through contextual feedback and semantic relevance during multi-turn of dialogue with a large model, resulting in the model producing unreasonable or harmful content. We evaluate CoA on different LLMs and datasets, and show that it can effectively expose the vulnerabilities of LLMs, and outperform existing attack methods. Our work provides a new perspective and tool for attacking and defending LLMs, and contributes to the security and ethical assessment of dialogue systems.