Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
Keywords: LLM, Large Language Model, safety alignment, augmentations, randomness, jailbreaks, attacks
TL;DR: We show that the safety alignment of state-of-the-art LLMs can be cheaply bypassed with simple random augmentations.
Abstract: Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking methods, such as adversarial attacks. However, these jailbreak methods can be rather costly or involve a non-trivial amount of creativity and effort, introducing the assumption that malicious users are high-resource or sophisticated. In this paper, we study how simple random augmentations to the input prompt affect safety alignment effectiveness in state-of-the-art LLMs, such as Llama 3 and Qwen 2. We perform an in-depth evaluation of 17 different models and investigate the intersection of safety under random augmentations with multiple dimensions: augmentation type, model size, quantization, fine-tuning-based defenses, and decoding strategies (e.g., sampling temperature). We show that low-resource and unsophisticated attackers, i.e. $\textit{stochastic monkeys}$, can significantly improve their chances of bypassing alignment with just 25 random augmentations per prompt.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11585
Loading