Annealing Self-Distillation Rectification Improves Adversarial Training

Published: 16 Jan 2024, Last Modified: 05 Mar 2024ICLR 2024 posterEveryoneRevisionsBibTeX
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: Adversarial training, Adversarial robustness
Submission Guidelines: I certify that this submission complies with the submission instructions as described on
TL;DR: We propose a data-driven label rectification technique to mitigate robust overfitting.
Abstract: In standard adversarial training, models are optimized to fit invariant one-hot labels for adversarial data when the perturbations are within allowable budgets. However, the overconfident target harms generalization and causes the problem of robust overfitting. To address this issue and enhance adversarial robustness, we analyze the characteristics of robust models and identify that robust models tend to produce smoother and well-calibrated outputs. Based on the observation, we propose a simple yet effective method, Annealing Self-Distillation Rectification (ADR), which generates soft labels as a better guidance mechanism that reflects the underlying distribution of data. By utilizing ADR, we can obtain rectified labels that improve model robustness without the need for pre-trained models or extensive extra computation. Moreover, our method facilitates seamless plug-and-play integration with other adversarial training techniques by replacing the hard labels in their objectives. We demonstrate the efficacy of ADR through extensive experiments and strong performances across datasets.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: zip
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: societal considerations including fairness, safety, privacy
Submission Number: 4379