Biblio

A plethora of recent work has shown that convolutional networks are not robust to adversarial images: images that are created by perturbing a sample from the data distribution as to maximize the loss on the perturbed example. In this work, we hypothesize that adversarial perturbations move the image away from the image manifold in the sense that there exists no physical process that could have produced the adversarial image. This hypothesis suggests that a successful defense mechanism against adversarial images should aim to project the images back onto the image manifold. We study such defense mechanisms, which approximate the projection onto the unknown image manifold by a nearest-neighbor search against a web-scale image database containing tens of billions of images. Empirical evaluations of this defense strategy on ImageNet suggest that it very effective in attack settings in which the adversary does not have access to the image database. We also propose two novel attack methods to break nearest-neighbor defense settings and show conditions under which nearest-neighbor defense fails. We perform a series of ablation experiments, which suggest that there is a trade-off between robustness and accuracy between as we use features from deeper in the network, that a large index size (hundreds of millions) is crucial to get good performance, and that careful construction of database is crucial for robustness against nearest-neighbor attacks.

Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. Our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 — it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by 10%. Code is available at https://github.com/facebookresearch/ImageNet-Adversarial-Training.