Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization
This work addresses the problem of adversarial attacks for deep learning practitioners by offering an incremental improvement through regularization to enhance model robustness.
The paper tackles the adversarial vulnerability of deep neural networks by analyzing the scale-variant property of cross-entropy loss and its impact on effective margin, proposing effective margin regularization (EMR) to maximize margins and boost robustness. The result shows that EMR outperforms adversarial training baselines like TRADES and enhances robustness when combined with methods like MART and MAIL, with substantial improvements on large-scale models.
The adversarial vulnerability of deep neural networks (DNNs) has been actively investigated in the past several years. This paper investigates the scale-variant property of cross-entropy loss, which is the most commonly used loss function in classification tasks, and its impact on the effective margin and adversarial robustness of deep neural networks. Since the loss function is not invariant to logit scaling, increasing the effective weight norm will make the loss approach zero and its gradient vanish while the effective margin is not adequately maximized. On typical DNNs, we demonstrate that, if not properly regularized, the standard training does not learn large effective margins and leads to adversarial vulnerability. To maximize the effective margins and learn a robust DNN, we propose to regularize the effective weight norm during training. Our empirical study on feedforward DNNs demonstrates that the proposed effective margin regularization (EMR) learns large effective margins and boosts the adversarial robustness in both standard and adversarial training. On large-scale models, we show that EMR outperforms basic adversarial training, TRADES and two regularization baselines with substantial improvement. Moreover, when combined with several strong adversarial defense methods (MART and MAIL), our EMR further boosts the robustness.