Feature Statistics with Uncertainty Help Adversarial Robustness

원문 초록

Despite the remarkable success of deep neural networks (DNNs), the security threat of adversarial attacks poses a significant challenge to the reliability of DNNs. By introducing randomness into different parts of DNNs, stochastic methods can enable the model to learn some uncertainty, thereby improving model robustness efficiently. In this paper, we theoretically discover a universal phenomenon that adversarial attacks will shift the distributions of feature statistics. Motivated by this theoretical finding, we propose a robustness enhancement module called Feature Statistics with Uncertainty (FSU). It resamples channel-wise feature means and standard deviations of examples from multivariate Gaussian distributions, which helps to reconstruct the attacked examples and calibrate the shifted distributions. The calibration recovers some domain characteristics of the data for classification, thereby mitigating the influence of perturbations and weakening the ability of attacks to deceive models. The proposed FSU module has universal applicability in training, attacking, predicting and fine-tuning, demonstrating impressive robustness enhancement ability at trivial additional time cost. For example, against powerful optimization-based CW attacks, by incorporating FSU into attacking and predicting phases, it endows many collapsed state-of-the-art models with 50%-80% robust accuracy on CIFAR10, CIFAR100 and SVHN.