On the Importance of Backbone to the Adversarial Robustness of Object Detectors

Xiao Li, Hang Chen, Xiaolin Hu

Keywords: adversarial robustness, object detection

TL;DR: A comprehensive study on how to improve the adversarial robustness of object detectors.

Abstract:

Object detection is a critical component of various security-sensitive applications, such as autonomous driving and video surveillance. However, existing object detectors are vulnerable to adversarial attacks, which poses a significant challenge to their reliability and safety.
Through experiments, first, we found that existing works on improving the adversarial robustness of object detectors give a false sense of security. Second, we found that using adversarially pre-trained backbone networks was essential for enhancing the adversarial robustness of object detectors. We then proposed a simple yet effective recipe for fast adversarial fine-tuning on object detectors with adversarially pre-trained backbones. Without any modifications to the structure of object detectors, our recipe achieved significantly better adversarial robustness than previous works. Finally, we explored the potential of different modern object detectors to improve adversarial robustness using our recipe and demonstrated interesting findings, which inspired us to design several state-of-the-art (SOTA) robust detectors with faster inference speed. Our empirical results set a new milestone for adversarially robust object detection. Code and trained checkpoints will be publicly available.

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.

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

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: 228