Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte entropy). However, the exploration of innocuous human-understandable malicious prompts augmented with adversarial injections remains limited. In this research, we explore converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. This allows us to show suffix conversion without any gradients, using only LLMs to perform the attacks, and thus better understand the scope of possible risks. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. The situations are extracted from the IMDB dataset, and prompts are defined following a few-shot chain-of-thought prompting. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs. We find that across many LLMs, as few as 1 attempt produces an attack and that these attacks transfer between LLMs.
Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models
Department of Computer Science, Stony Brook University(石英布大学计算机科学系);Oslo Metropolitan University, Oslo Business School(奥斯陆 Metropolitan 大学奥斯陆商学院);University of Texas at Dallas, Dept. of Psychology(德克萨斯大学达拉斯分校心理学系)
Interpretable Adversarial Perturbation in Input Embedding Space for Text
Preferred Networks, Inc.(优选网络公司);Nara Institute of Science and Technology(奈良先端科学技术大学院大学);RIKEN AIP(理化学研究所先进智能项目中心);Tohoku University(东北大学);NTT Communication Science Laboratories(日本电信电话通信科学实验室)