Related papers: Playing it Safe: Adversarial Robustness with an Ab…
Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training, which makes the overall classifier robust, it does not…
We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods. While one of the classical setups in online learning deals with the "adversarial"…
Deep reinforcement learning (DRL) policies have been shown to be deceived by perturbations (e.g., random noise or intensional adversarial attacks) on state observations that appear at test time but are unknown during training. To increase…
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy…
Adversarial examples are some special input that can perturb the output of a deep neural network, in order to make produce intentional errors in the learning algorithms in the production environment. Most of the present methods for…
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…
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified…
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…
Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…
Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…
We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions from features to…
Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…
Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted to training environments, RL methods have often failed to be…
Contrastive Learning first extracts features from unlabeled data, followed by linear probing with labeled data. Adversarial Contrastive Learning (ACL) integrates Adversarial Training into the first phase to enhance feature robustness…
Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mistakes the previous model did not make. Such…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
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…
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…
Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the…
Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…