Posted Content•
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
TL;DR: In this article, a general hardness reduction between detection and classification of adversarial examples is proposed, where given a robust detector for attacks at distance ω(n) in some metric, a similarly robust (but inefficient) classifier for attacks ω (n)/2.
Abstract: Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and classification of adversarial examples: given a robust detector for attacks at distance {\epsilon} (in some metric), we can build a similarly robust (but inefficient) classifier for attacks at distance {\epsilon}/2. Our reduction is computationally inefficient, and thus cannot be used to build practical classifiers. Instead, it is a useful sanity check to test whether empirical detection results imply something much stronger than the authors presumably anticipated. To illustrate, we revisit 13 detector defenses. For 11/13 cases, we show that the claimed detection results would imply an inefficient classifier with robustness far beyond the state-of-the-art.
Citations
More filters
Posted Content•
TL;DR: PatchCleanser as mentioned in this paper performs two rounds of pixel masking on the input image to neutralize the effect of the adversarial patch, which achieves state-of-the-art certified robustness.
Abstract: The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a localized restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical world by printing and attaching the patch to the victim object and thus imposes a real-world threat to computer vision systems. To counter this threat, we propose PatchCleanser as a certifiably robust defense against adversarial patches that is compatible with any image classifier. In PatchCleanser, we perform two rounds of pixel masking on the input image to neutralize the effect of the adversarial patch. In the first round of masking, we apply a set of carefully generated masks to the input image and evaluate the model prediction on every masked image. If model predictions on all one-masked images reach a unanimous agreement, we output the agreed prediction label. Otherwise, we perform a second round of masking to settle the disagreement, in which we evaluate model predictions on two-masked images to robustly recover the correct prediction label. Notably, we can prove that our defense will always make correct predictions on certain images against any adaptive white-box attacker within our threat model, achieving certified robustness. We extensively evaluate our defense on the ImageNet, ImageNette, CIFAR-10, CIFAR-100, SVHN, and Flowers-102 datasets and demonstrate that our defense achieves similar clean accuracy as state-of-the-art classification models and also significantly improves certified robustness from prior works. Notably, our defense can achieve 83.8% top-1 clean accuracy and 60.4% top-1 certified robust accuracy against a 2%-pixel square patch anywhere on the 1000-class ImageNet dataset.
References
More filters
Proceedings Article•
01 Jan 2014TL;DR: It is found that there is no distinction between individual highlevel units and random linear combinations of high level units, according to various methods of unit analysis, and it is suggested that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks.
Abstract: Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn uninterpretable solutions that could have counter-intuitive properties. In this paper we report two such properties.
First, we find that there is no distinction between individual high level units and random linear combinations of high level units, according to various methods of unit analysis. It suggests that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks.
Second, we find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extend. We can cause the network to misclassify an image by applying a certain imperceptible perturbation, which is found by maximizing the network's prediction error. In addition, the specific nature of these perturbations is not a random artifact of learning: the same perturbation can cause a different network, that was trained on a different subset of the dataset, to misclassify the same input.
9,561 citations
Proceedings Article•
15 Feb 2018TL;DR: This article studied the adversarial robustness of neural networks through the lens of robust optimization and identified methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Abstract: Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples—inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides us with a broad and unifying view on much of the prior work on this topic. Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal. In particular, they specify a concrete security guarantee that would protect against any adversary. These methods let us train networks with significantly improved resistance to a wide range of adversarial attacks. They also suggest the notion of security against a first-order adversary as a natural and broad security guarantee. We believe that robustness against such well-defined classes of adversaries is an important stepping stone towards fully resistant deep learning models. Code and pre-trained models are available at this https URL and this https URL.
3,581 citations
03 Nov 2017
TL;DR: In this paper, the authors survey ten recent proposals for adversarial examples and compare their efficacy, concluding that all can be defeated by constructing new loss functions, and propose several simple guidelines for evaluating future proposed defenses.
Abstract: Neural networks are known to be vulnerable to adversarial examples: inputs that are close to natural inputs but classified incorrectly. In order to better understand the space of adversarial examples, we survey ten recent proposals that are designed for detection and compare their efficacy. We show that all can be defeated by constructing new loss functions. We conclude that adversarial examples are significantly harder to detect than previously appreciated, and the properties believed to be intrinsic to adversarial examples are in fact not. Finally, we propose several simple guidelines for evaluating future proposed defenses.
1,703 citations
Proceedings Article•
01 Jan 2018TL;DR: This paper proposes a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier, and obtains the class conditional Gaussian distributions with respect to (low- and upper-level) features of the deep models under Gaussian discriminant analysis.
Abstract: Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier. We obtain the class conditional Gaussian distributions with respect to (low- and upper-level) features of the deep models under Gaussian discriminant analysis, which result in a confidence score based on the Mahalanobis distance. While most prior methods have been evaluated for detecting either out-of-distribution or adversarial samples, but not both, the proposed method achieves the state-of-the-art performances for both cases in our experiments. Moreover, we found that our proposed method is more robust in harsh cases, e.g., when the training dataset has noisy labels or small number of samples. Finally, we show that the proposed method enjoys broader usage by applying it to class-incremental learning: whenever out-of-distribution samples are detected, our classification rule can incorporate new classes well without further training deep models.
1,022 citations
01 Jan 2018
Abstract: Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.
969 citations