相关论文: Stronger and Faster Wasserstein Adversarial Attack…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Video-based object detection plays a vital role in safety-critical applications. While deep learning-based object detectors have achieved impressive performance, they remain vulnerable to adversarial attacks, particularly those involving…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

Generative Adversarial Networks are a popular method for learning distributions from data by modeling the target distribution as a function of a known distribution. The function, often referred to as the generator, is optimized to minimize…

Despite its popularity, deep neural networks are easily fooled. To alleviate this deficiency, researchers are actively developing new training strategies, which encourage models that are robust to small input perturbations. Several…

Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this…

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence…

Wasserstein Discriminant Analysis (WDA) is a new supervised method that can improve classification of high-dimensional data by computing a suitable linear map onto a lower dimensional subspace. Following the blueprint of classical Linear…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Generative modelling is often cast as minimizing a similarity measure between a data distribution and a model distribution. Recently, a popular choice for the similarity measure has been the Wasserstein metric, which can be expressed in the…

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target…

Adversarially robust optimization (ARO) has emerged as the *de facto* standard for training models that hedge against adversarial attacks in the test stage. While these models are robust against adversarial attacks, they tend to suffer…

In this work, we introduce a novel framework for privately optimizing objectives that rely on Wasserstein distances between data-dependent empirical measures. Our main theoretical contribution is, based on an explicit formulation of the…

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Motivated by the 2D class averaging problem in single-particle cryo-electron microscopy (cryo-EM), we present a k-means algorithm based on a rotationally-invariant Wasserstein metric for images. Unlike existing methods that are based on…

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization…

Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret…

Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions. Learning objectives approximately minimize an $f$-divergence ($f$-GANs) or an integral probability metric (Wasserstein GANs)…

Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being…

Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications. However, this framework has two main drawbacks: (i) Wasserstein-1 (or Earth-Mover)…