Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when attacking a deployed machine learning service, one can only acquire the input-output correspondences of the target model; this is the so-called black-box attack setting. The major drawback of existing black-box attacks is the need for excessive model queries, which may give a false sense of model robustness due to inefficient query designs. To bridge this gap, we propose a generic framework for query-efficient black-box attacks. Our framework, AutoZOOM, which is short for Autoencoder-based Zeroth Order Optimization Method, has two novel building blocks towards efficient black-box attacks: (i) an adaptive random gradient estimation strategy to balance query counts and distortion, and (ii) an autoencoder that is either trained offline with unlabeled data or a bilinear resizing operation for attack acceleration. Experimental results suggest that, by applying AutoZOOM to a state-of-the-art black-box attack (ZOO), a significant reduction in model queries can be achieved without sacrificing the attack success rate and the visual quality of the resulting adversarial examples. In particular, when compared to the standard ZOO method, AutoZOOM can consistently reduce the mean query counts in finding successful adversarial examples (or reaching the same distortion level) by at least 93% on MNIST, CIFAR-10 and ImageNet datasets, leading to novel insights on adversarial robustness.
We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumption of continuous-valued confidence scores, our highly query-efficient algorithm utilizes the following simple iterative principle: we randomly sample a vector from a predefined orthonormal basis and either add or subtract it to the target image. Despite its simplicity, the proposed method can be used for both untargeted and targeted attacks -- resulting in previously unprecedented query efficiency in both settings. We demonstrate the efficacy and efficiency of our algorithm on several real world settings including the Google Cloud Vision API. We argue that our proposed algorithm should serve as a strong baseline for future black-box attacks, in particular because it is extremely fast and its implementation requires less than 20 lines of PyTorch code.
Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model of full query access. We define three realistic threat models that more accurately characterize many real-world classifiers: the query-limited setting, the partial-information setting, and the label-only setting. We develop new attacks that fool classifiers under these more restrictive threat models, where previous methods would be impractical or ineffective. We demonstrate that our methods are effective against an ImageNet classifier under our proposed threat models. We also demonstrate a targeted black-box attack against a commercial classifier, overcoming the challenges of limited query access, partial information, and other practical issues to attack the Google Cloud Vision API.
This paper addresses the challenging black-box adversarial attack problem, where only classification confidence of a victim model is available. Inspired by consistency of visual saliency between different vision models, a surrogate model is expected to improve the attack performance via transferability. By combining transferability-based and query-based black-box attack, we propose a surprisingly simple baseline approach (named SimBA++) using the surrogate model, which significantly outperforms several state-of-the-art methods. Moreover, to efficiently utilize the query feedback, we update the surrogate model in a novel learning scheme, named High-Order Gradient Approximation (HOGA). By constructing a high-order gradient computation graph, we update the surrogate model to approximate the victim model in both forward and backward pass. The SimBA++ and HOGA result in Learnable Black-Box Attack (LeBA), which surpasses previous state of the art by considerable margins: the proposed LeBA significantly reduces queries, while keeping higher attack success rates close to 100% in extensive ImageNet experiments, including attacking vision benchmarks and defensive models. Code is open source at https://github.com/TrustworthyDL/LeBA.
October 1, 2019 Abstract We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization (BO) to specifically cater to scenarios involving low query budgets to develop query efficient adversarial attacks. We alleviate the issues surrounding BO in regards to optimizing high dimensional deep learning models by effective dimension upsampling techniques. Our proposed approach achieves performance comparable to the state of the art black-box adversarial attacks albeit with a much lower average query count. In particular, in low query budget regimes, our proposed method reduces the query count up to 80% with respect to the state of the art methods. 1 Introduction Neural networks are now well-known to be vulnerable to adversarial examples: additive perturbations that, when applied to the input, change the network's output classification . Work investigating this lack of robustness to adversarial examples often takes the form of a back-and-forth between newly proposed adversarial attacks, methods for quickly and efficiently crafting adversarial examples, and corresponding defenses that modify the classifier at either training or test time to improve robustness. The most successful adversarial attacks use gradient-based optimization methods [9, 17], which require complete knowledge of the architecture and parameters of the target network; this assumption is referred to as the white-box attack setting.