Related papers: A Black-box Attack on Neural Networks Based on Swa…

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on…

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…

Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vulnerability in…

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may…

Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…

The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

NeuroEvolution automates the generation of Artificial Neural Networks through the application of techniques from Evolutionary Computation. The main goal of these approaches is to build models that maximize predictive performance, sometimes…

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…

We aim at demonstrating the influence of diversity in the ensemble of CNNs on the detection of black-box adversarial instances and hardening the generation of white-box adversarial attacks. To this end, we propose an ensemble of diverse…

While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and…

Clustering algorithms are used in a large number of applications and play an important role in modern machine learning-- yet, adversarial attacks on clustering algorithms seem to be broadly overlooked unlike supervised learning. In this…

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by…

Neuroevolution automates the complex task of neural network design but often ignores the inherent adversarial fragility of evolved models which is a barrier to adoption in safety-critical scenarios. While robust training methods have…

Researches have shown that deep neural networks are vulnerable to malicious attacks, where adversarial images are created to trick a network into misclassification even if the images may give rise to totally different labels by human eyes.…

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph structure related tasks such as node classification and graph classification. However, GNNs are vulnerable to adversarial attacks. Existing works…

As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been found vulnerable to targeted attacks which cause them to produce…

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has…

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness…