We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased inference-time compute leads to improved robustness. In many cases (with important exceptions), the fraction of model samples where the attack succeeds tends to zero as the amount of test-time compute grows. We perform no adversarial training for the tasks we study, and we increase inference-time compute by simply allowing the models to spend more compute on reasoning, independently of the form of attack. Our results suggest that inference-time compute has the potential to improve adversarial robustness for Large Language Models. We also explore new attacks directed at reasoning models, as well as settings where inference-time compute does not improve reliability, and speculate on the reasons for these as well as ways to address them.
@article{arxiv.2501.18841,
title = {Trading Inference-Time Compute for Adversarial Robustness},
author = {Wojciech Zaremba and Evgenia Nitishinskaya and Boaz Barak and Stephanie Lin and Sam Toyer and Yaodong Yu and Rachel Dias and Eric Wallace and Kai Xiao and Johannes Heidecke and Amelia Glaese},
journal= {arXiv preprint arXiv:2501.18841},
year = {2025}
}