相关论文: Guided Interpolation for Adversarial Training

Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the…

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…

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…

Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can…

Generative adversarial networks, which can generate metasurfaces based on a training set of high performance device layouts, have the potential to significantly reduce the computational cost of the metasurface design process. However, basic…

We propose the novel framework for generative modelling using hybrid energy-based models. In our method we combine the interpretable input gradients of the robust classifier and Langevin Dynamics for sampling. Using the adversarial training…

Being able to cooperate with diverse humans is an important component of many economically valuable AI tasks, from household robotics to autonomous driving. However, generalizing to novel humans requires training on data that captures the…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…

Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent…

Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the final robustness of models during AT, that is, the so-called…

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

In this paper, we propose a new framework for mitigating biases in machine learning systems. The problem of the existing mitigation approaches is that they are model-oriented in the sense that they focus on tuning the training algorithms to…

Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, training samples obey invariances that are \textit{a priori}…

Fast adversarial training (FAT) is an efficient method to improve robustness. However, the original FAT suffers from catastrophic overfitting, which dramatically and suddenly reduces robustness after a few training epochs. Although various…

Graph neural network (GNN) explanations have largely been facilitated through post-hoc introspection. While this has been deemed successful, many post-hoc explanation methods have been shown to fail in capturing a model's learned…

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust…

Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally…

Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a…