@article{improvingalignmentandrobustnesswithshort, title = {Improving Alignment and Robustness with Circuit Breakers}, author = {Andy Zou and Long Phan and Justin Wang and Derek Duenas and Maxwell Lin and Maksym Andriushchenko and Rowan Wang and Zico Kolter and Matt Fredrikson and Dan Hendrycks}, year = {2024}, eprint = {2406.04313}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.04313v4}, }