A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which lead to incorrect predictions. Unfortunately, most literature focuses on visually imperceivable perturbations to be applied to digital images that often are, by design, impossible to be deployed to physical targets. We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks. Adversarial Scratches leverage B\'ezier Curves to reduce the dimension of the search space and possibly constrain the attack to a specific location. We test Adversarial Scratches in several scenarios, including a publicly available API and images of traffic signs. Results show that, often, our attack achieves higher fooling rate than other deployable state-of-the-art methods, while requiring significantly fewer queries and modifying very few pixels.
相關內容
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible. To solve these problems, we propose a two-phase and image-specific triggers generation method to enhance clean-label backdoor attacks. Our methods are (1) powerful: our triggers can both promote the two phases (i.e., the backdoor implantation and activation phase) in backdoor attacks simultaneously; (2) stealthy: our triggers are generated from each image. They are image-specific instead of fixed triggers. Extensive experiments demonstrate that our approach can achieve a fantastic attack success rate~(98.98%) with low poisoning rate~(5%), high stealthiness under many evaluation metrics and is resistant to backdoor defense methods.
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: //github.com/UMBCvision/SSL-Backdoor .
Text-based adversarial attacks are becoming more commonplace and accessible to general internet users. As these attacks proliferate, the need to address the gap in model robustness becomes imminent. While retraining on adversarial data may increase performance, there remains an additional class of character-level attacks on which these models falter. Additionally, the process to retrain a model is time and resource intensive, creating a need for a lightweight, reusable defense. In this work, we propose the Adversarial Text Normalizer, a novel method that restores baseline performance on attacked content with low computational overhead. We evaluate the efficacy of the normalizer on two problem areas prone to adversarial attacks, i.e. Hate Speech and Natural Language Inference. We find that text normalization provides a task-agnostic defense against character-level attacks that can be implemented supplementary to adversarial retraining solutions, which are more suited for semantic alterations.
Deep learning systems are known to be vulnerable to adversarial examples. In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the network by submitting queries and inspecting returns. Recent work largely improves the efficiency of those attacks, demonstrating their practicality on today's ML-as-a-service platforms. We propose Blacklight, a new defense against query-based black-box adversarial attacks. The fundamental insight driving our design is that, to compute adversarial examples, these attacks perform iterative optimization over the network, producing image queries highly similar in the input space. Blacklight detects query-based black-box attacks by detecting highly similar queries, using an efficient similarity engine operating on probabilistic content fingerprints. We evaluate Blacklight against eight state-of-the-art attacks, across a variety of models and image classification tasks. Blacklight identifies them all, often after only a handful of queries. By rejecting all detected queries, Blacklight prevents any attack to complete, even when attackers persist to submit queries after account ban or query rejection. Blacklight is also robust against several powerful countermeasures, including an optimal black-box attack that approximates white-box attacks in efficiency. Finally, we illustrate how Blacklight generalizes to other domains like text classification.
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we propose a new adversarial training algorithm that is theoretically well motivated and empirically superior to other existing algorithms. A novel feature of the proposed algorithm is to use a data-adaptive regularization for robustifying a prediction model. We apply more regularization to data which are more vulnerable to adversarial attacks and vice versa. Even though the idea of data-adaptive regularization is not new, our data-adaptive regularization has a firm theoretical base of reducing an upper bound of the robust risk. Numerical experiments illustrate that our proposed algorithm improves the generalization (accuracy on clean samples) and robustness (accuracy on adversarial attacks) simultaneously to achieve the state-of-the-art performance.
Recent work has illuminated the vulnerability of speaker recognition systems (SRSs) against adversarial attacks, raising significant security concerns in deploying SRSs. However, they considered only a few settings (e.g., some combinations of source and target speakers), leaving many interesting and important settings in real-world attack scenarios alone. In this work, we present AS2T, the first attack in this domain which covers all the settings, thus allows the adversary to craft adversarial voices using arbitrary source and target speakers for any of three main recognition tasks. Since none of the existing loss functions can be applied to all the settings, we explore many candidate loss functions for each setting including the existing and newly designed ones. We thoroughly evaluate their efficacy and find that some existing loss functions are suboptimal. Then, to improve the robustness of AS2T towards practical over-the-air attack, we study the possible distortions occurred in over-the-air transmission, utilize different transformation functions with different parameters to model those distortions, and incorporate them into the generation of adversarial voices. Our simulated over-the-air evaluation validates the effectiveness of our solution in producing robust adversarial voices which remain effective under various hardware devices and various acoustic environments with different reverberation, ambient noises, and noise levels. Finally, we leverage AS2T to perform thus far the largest-scale evaluation to understand transferability among 14 diverse SRSs. The transferability analysis provides many interesting and useful insights which challenge several findings and conclusion drawn in previous works in the image domain. Our study also sheds light on future directions of adversarial attacks in the speaker recognition domain.
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model security. In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of \textbf{32 base attackers}. We design a search space where attack policy is represented as an attacking sequence, i.e., the output of the previous attacker is used as the initialization input for successors. Multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity. The experimental result shows CAA beats 10 top attackers on 11 diverse defenses with less elapsed time (\textbf{6 $\times$ faster than AutoAttack}), and achieves the new state-of-the-art on $l_{\infty}$, $l_{2}$ and unrestricted adversarial attacks.
While existing work in robust deep learning has focused on small pixel-level $\ell_p$ norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations -- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.
Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works have shown those algorithms, which can even surpass the human capabilities, are vulnerable to adversarial examples. In Computer Vision, adversarial examples are images containing subtle perturbations generated by malicious optimization algorithms in order to fool classifiers. As an attempt to mitigate these vulnerabilities, numerous countermeasures have been constantly proposed in literature. Nevertheless, devising an efficient defense mechanism has proven to be a difficult task, since many approaches have already shown to be ineffective to adaptive attackers. Thus, this self-containing paper aims to provide all readerships with a review of the latest research progress on Adversarial Machine Learning in Image Classification, however with a defender's perspective. Here, novel taxonomies for categorizing adversarial attacks and defenses are introduced and discussions about the existence of adversarial examples are provided. Further, in contrast to exisiting surveys, it is also given relevant guidance that should be taken into consideration by researchers when devising and evaluating defenses. Finally, based on the reviewed literature, it is discussed some promising paths for future research.
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. A network based on 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 and models will be made publicly available.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191