Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using carefully constructed prompts. In our study, we reveal a new threat to LLM alignment when a bad actor has access to the model's output logits, a common feature in both open-source LLMs and many commercial LLM APIs (e.g., certain GPT models). It does not rely on crafting specific prompts. Instead, it exploits the fact that even when an LLM rejects a toxic request, a harmful response often hides deep in the output logits. By forcefully selecting lower-ranked output tokens during the auto-regressive generation process at a few critical output positions, we can compel the model to reveal these hidden responses. We term this process model interrogation. This approach differs from and outperforms jail-breaking methods, achieving 92% effectiveness compared to 62%, and is 10 to 20 times faster. The harmful content uncovered through our method is more relevant, complete, and clear. Additionally, it can complement jail-breaking strategies, with which results in further boosting attack performance. Our findings indicate that interrogation can extract toxic knowledge even from models specifically designed for coding tasks.
@article{arxiv.2312.04782,
title = {Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs},
author = {Zhuo Zhang and Guangyu Shen and Guanhong Tao and Siyuan Cheng and Xiangyu Zhang},
journal= {arXiv preprint arXiv:2312.04782},
year = {2023}
}