Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
Preprint
Abstract
Adversarial Training (AT) has been demonstrated to improve the robustness of deep neural networks (DNNs) against adversarial attacks. AT is a min-max optimization procedure where in adversarial examples are generated to train a more robust DNN. The inner maximization step of AT increases the losses of inputs with respect to their actual classes. The outer minimization involves minimizing the losses on the adversarial examples obtained from the inner maximization. This work proposes a standard-deviation-inspired (SDI) regularization term to improve adversarial robustness and generalization. We argue that the inner maximization in AT is similar to minimizing a modified standard deviation of the model's output probabilities. Moreover, we suggest that maximizing this modified standard deviation can complement the outer minimization of the AT framework. To support our argument, we experimentally show that the SDI measure can be used to craft adversarial examples. Additionally, we demonstrate that combining the SDI regularization term with existing AT variants enhances the robustness of DNNs against stronger attacks, such as CW and Auto-attack, and improves generalization.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Extreme Miscalibration and the Illusion of Adversarial Robustness2024
- Gradient Masking of Label Smoothing in Adversarial RobustnessIEEE Access, 2020
- Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss2019
- The Limitations of Deep Learning in Adversarial Settings2016
- Empirical Margin Distributions and Bounding the Generalization Error of Combined ClassifiersThe Annals of Statistics, 2002
- Coherent Measures of RiskMathematical Finance, 1999