相关论文: Nonlinear Projection Based Gradient Estimation for…

The goal of No-Reference Image Quality Assessment (NR-IQA) is to predict the perceptual quality of an image in line with its subjective evaluation. To put the NR-IQA models into practice, it is essential to study their potential loopholes…

We propose the Square Attack, a score-based black-box $l_2$- and $l_\infty$-adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. Square Attack is based on a randomized search…

No-Reference Video Quality Assessment (NR-VQA) plays an essential role in improving the viewing experience of end-users. Driven by deep learning, recent NR-VQA models based on Convolutional Neural Networks (CNNs) and Transformers have…

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…

Graph Neural Networks (GNNs) have received significant attention due to their state-of-the-art performance on various graph representation learning tasks. However, recent studies reveal that GNNs are vulnerable to adversarial attacks, i.e.…

Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone small, carefully crafted perturbations, and which can easily fool a DNN into making misclassifications at test…

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial…

Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…

In order to be applicable in real-world scenario, Boundary Attacks (BAs) were proposed and ensured one hundred percent attack success rate with only decision information. However, existing BA methods craft adversarial examples by leveraging…

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the malware's API call sequences and non-sequential features…

Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency and usually imposing…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant…

While convolutional neural networks (CNNs) have achieved success in computer vision tasks, it is vulnerable to backdoor attacks. Such attacks could mislead the victim model to make attacker-chosen prediction with a specific trigger pattern.…

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…

One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign…

Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number…

Machine learning models are critically susceptible to evasion attacks from adversarial examples. Generally, adversarial examples, modified inputs deceptively similar to the original input, are constructed under whitebox settings by…