Related papers: Dynamic Perturbation-Adaptive Adversarial Training…
Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification…
Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (DA) parameters along with AN, which poses a greater threat to…
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to those corruptions but may harm performance on clean images…
Object detectors encounter challenges in handling domain shifts. Cutting-edge domain adaptive object detection methods use the teacher-student framework and domain adversarial learning to generate domain-invariant pseudo-labels for…
In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of…
Deep learning methods have shown impressive results for a variety of medical problems over the last few years. However, datasets tend to be small due to time-consuming annotation. As datasets with different patients are often very…
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of…
Deep learning (DL) has been widely applied to enhance automatic modulation classification (AMC). However, the elaborate AMC neural networks are susceptible to various adversarial attacks, which are challenging to handle due to the…
Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperceptible adversarial perturbations. While adversarial training (AT) has proven to be an effective defense approach, the AT mechanism for robustness improvement is not…
Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve the accuracy and…
A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…
This work systematically investigates the adversarial robustness of deep image denoisers (DIDs), i.e, how well DIDs can recover the ground truth from noisy observations degraded by adversarial perturbations. Firstly, to evaluate DIDs'…
In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…
Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally…
Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (self-AT) remains…
Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…
In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…
Deep learning models have achieved state-of-the-art performances in various domains, while they are vulnerable to the inputs with well-crafted but small perturbations, which are named after adversarial examples (AEs). Among many strategies…
In this paper, we propose the physics informed adversarial training (PIAT) of neural networks for solving nonlinear differential equations (NDE). It is well-known that the standard training of neural networks results in non-smooth…