相关论文: Optimal Transport as a Defense Against Adversarial…

In this paper, we propose to tackle the problem of reducing discrepancies between multiple domains referred to as multi-source domain adaptation and consider it under the target shift assumption: in all domains we aim to solve a…

Despite impressive success in many tasks, deep learning models are shown to rely on spurious features, which will catastrophically fail when generalized to out-of-distribution (OOD) data. Invariant Risk Minimization (IRM) is proposed to…

Recent work has demonstrated that neural networks are vulnerable to adversarial examples. To escape from the predicament, many works try to harden the model in various ways, in which adversarial training is an effective way which learns…

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output…

The phenomenon of adversarial examples illustrates one of the most basic vulnerabilities of deep neural networks. Among the variety of techniques introduced to surmount this inherent weakness, adversarial training has emerged as the most…

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at…

Neural network-based optimal transport (OT) is a recent and fruitful direction in the generative modeling community. It finds its applications in various fields such as domain translation, image super-resolution, computational biology and…

Deep neural networks remain highly vulnerable to adversarial examples, and most defenses collapse once gradients can be reliably estimated. We identify \emph{gradient consensus} -- the tendency of randomized transformations to yield aligned…

We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning. We propose and analyze a novel min-max framework that seeks a representation which minimizes the maximum…

Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…

Deep neural networks (DNNs) are known to be vulnerable to adversarial perturbations, which imposes a serious threat to DNN-based decision systems. In this paper, we propose to apply the lossy Saak transform to adversarially perturbed images…

An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an…

Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which…

Deep learning has been a popular topic and has achieved success in many areas. It has drawn the attention of researchers and machine learning practitioners alike, with developed models deployed to a variety of settings. Along with its…

Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection. However, these algorithms are extremely sensitive to over-fitting, domain…

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…