Related papers: Tricking Adversarial Attacks To Fail

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as…

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…

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…

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

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…

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each…

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…

Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work, inspired by…

Motivated by the superior performance of deep learning in many applications including computer vision and natural language processing, several recent studies have focused on applying deep neural network for devising future generations of…

Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging.…

Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad…

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Adversarial examples represent a serious issue for the application of machine learning models in many sensitive domains. For generating adversarial examples, decision based black-box attacks are one of the most practical techniques as they…

Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…

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…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose…