Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose Manifold-…
Adversarial RobustnessDisentangled Deep Autoencoding Regularization for Robust Image Classification
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with…
ClassificationGeneral Classificationimage-classificationImage Classification+1Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convoluti…
Adversarial AttackAdversarial RobustnessSensitivitySmooth Kernels Improve Adversarial Robustness and Perceptually-Aligned Gradients
Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns. Inspired by the intuition that humans are more sensitive to the lower-frequency (larger-scale) patterns we design a regu…
Adversarial RobustnessTowards Robustness of Deep Neural Networks via Regularization
Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples. Inspired by the observation that adversarial examples often lie outside the natural image data manifold and the…
Adversarial AttackAdversarial Robustness