Enhancing Certified Robustness via Block Reflector Orthogonal Layers

ICLR 2025 Conference Submission1070 Authors

Keywords: Certified robustness, Adversarial

TL;DR: We propose a new orthogonal convolution and a novel loss function to enhance certified robustness.

Abstract:

Lipschitz neural networks are well-known for providing certified robustness in deep learning. In this paper, we present a novel efficient Block Reflector Orthogonal layer that enables the construction of simple yet effective Lipschitz neural networks.
In addition, by theoretically analyzing the nature of Lipschitz neural networks, we introduce a new loss function that employs an annealing mechanism to improve margin for most data points.
This enables Lipschitz models to provide better certified robustness.
By employing our BRO layer and loss function, we design BRONet, which provides state-of-the-art certified robustness.
Extensive experiments and empirical analysis on CIFAR-10, CIFAR-100, and Tiny-ImageNet validate that our method outperforms existing baselines.

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: 1070