相关论文: Parsimonious Black-Box Adversarial Attacks via Eff…

Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has query access to the…

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…

Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite…

Neural networks have demonstrated remarkable success in learning and solving complex tasks in a variety of fields. Nevertheless, the rise of those networks in modern computing has been accompanied by concerns regarding their vulnerability…

Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output. Existing black-box methods for…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…

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,…

This paper deals with the black-box optimization problem. In this setup, we do not have access to the gradient of the objective function, therefore, we need to estimate it somehow. We propose a new type of approximation JAGUAR, that…

We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the…

The output of Deep Neural Networks (DNN) can be altered by a small perturbation of the input in a black box setting by making multiple calls to the DNN. However, the high computation and time required makes the existing approaches unusable.…

Traffic state prediction is necessary for many Intelligent Transportation Systems applications. Recent developments of the topic have focused on network-wide, multi-step prediction, where state of the art performance is achieved via deep…

Black-box optimization is primarily important for many compute-intensive applications, including reinforcement learning (RL), robot control, etc. This paper presents a novel theoretical framework for black-box optimization, in which our…

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to original images. Most existing adversarial attack methods achieve nearly 100% attack success rates under the…

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain…

Although deep neural networks have been very successful in image-classification tasks, they are prone to adversarial attacks. To generate adversarial inputs, there has emerged a wide variety of techniques, such as black- and whitebox…

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed…

It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are…

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose…