Related papers: Adversarial Robust Memory-Based Continual Learner

Robust streaming, the study of streaming algorithms that provably work when the stream is generated by an adaptive adversary, has seen tremendous progress in recent years. However, fundamental barriers remain: the best known algorithm for…

While many defences against adversarial examples have been proposed, finding robust machine learning models is still an open problem. The most compelling defence to date is adversarial training and consists of complementing the training…

Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…

Learning-based pattern classifiers, including deep networks, have shown impressive performance in several application domains, ranging from computer vision to cybersecurity. However, it has also been shown that adversarial input…

Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Deep learning technology has made great achievements in the field of image. In order to defend against malware attacks, researchers have proposed many Windows malware detection models based on deep learning. However, deep learning models…

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…

Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic adversarial threats. The…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Adversarial attacks and defenses in machine learning and deep neural network have been gaining significant attention due to the rapidly growing applications of deep learning in the Internet and relevant scenarios. This survey provides a…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection…

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model…

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem…

Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…