Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

Zeyang Sha, Xinlei He, Pascal Berrang, Mathias Humbert, Yang Zhang

Primary Area: societal considerations including fairness, safety, privacy

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.

Keywords: Backdoor Defense, Fine-tuning, Backdoor Sequela

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract:

Backdoor attacks represent one of the major threats to machine learning models.
Various efforts have been made to mitigate backdoors.
However, existing defenses have become increasingly complex and often require high computational resources or may also jeopardize models' utility.
In this work, we show that fine-tuning, one of the most common and easy-to-adopt machine learning training operations, can effectively remove backdoors from machine learning models while maintaining high model utility.
Extensive experiments over three machine learning paradigms show that fine-tuning and our newly proposed super-fine-tuning achieve strong defense performance.
We hope our results can help machine learning model owners better protect their models from backdoor threats.
Also, it calls for the design of more advanced attacks in order to comprehensively assess machine learning models' backdoor vulnerabilities.

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: 5421