相关论文: Effective Targeted Attacks for Adversarial Self-Su…

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an "attack"…

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their…

As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide sufficient assurance or…

Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such…

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

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…

Self-supervised learning (SSL) is a growing torrent that has recently transformed machine learning and its many real world applications, by learning on massive amounts of unlabeled data via self-generated supervisory signals. Unsupervised…

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Adversarial robustness is a research area that has recently received a lot of attention in the quest for trustworthy artificial intelligence. However, recent works on adversarial robustness have focused on supervised learning where it is…

Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…

This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to…

Decision making and learning in the presence of uncertainty has attracted significant attention in view of the increasing need to achieve robust and reliable operations. In the case where uncertainty stems from the presence of adversarial…

The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori probabilities in…

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversarial perturbations to…

Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models. However, previous works…