Related papers: Wasserstein Adversarial Examples via Projected Sin…
In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and…
In this paper, we analyze deep learning from a mathematical point of view and derive several novel results. The results are based on intriguing mathematical properties of high dimensional spaces. We first look at perturbation based…
Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel…
Failure cases of black-box deep learning, e.g. adversarial examples, might have severe consequences in healthcare. Yet such failures are mostly studied in the context of real-world images with calibrated attacks. To demystify the…
Adding perturbations to images can mislead classification models to produce incorrect results. Recently, researchers exploited adversarial perturbations to protect image privacy from retrieval by intelligent models. However, adding…
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework,…
It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…
Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft adversarial…
Adversarial classification is the task of performing robust classification in the presence of a strategic attacker. Originating from information hiding and multimedia forensics, adversarial classification recently received a lot of…
Lack of ground-truth MR images impedes the common supervised training of neural networks for image reconstruction. To cope with this challenge, this paper leverages unpaired adversarial training for reconstruction networks, where the inputs…
Artificial neural networks are prone to being fooled by carefully perturbed inputs which cause an egregious misclassification. These \textit{adversarial} attacks have been the focus of extensive research. Likewise, there has been an…
Attributing the pixels of an input image to a certain category is an important and well-studied problem in computer vision, with applications ranging from weakly supervised localisation to understanding hidden effects in the data. In recent…
With the excellent accuracy and feasibility, the Neural Networks have been widely applied into the novel intelligent applications and systems. However, with the appearance of the Adversarial Attack, the NN based system performance becomes…
It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) method, by incorporating adversarial examples during…
Convolutional Neural Networks (CNN) based methods have significantly improved the performance of image steganalysis compared with conventional ones based on hand-crafted features. However, many existing literatures on computer vision have…
This paper addresses a new active learning strategy for regression problems. The presented Wasserstein active regression model is based on the principles of distribution-matching to measure the representativeness of the labeled dataset. The…
Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions.…
Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human…
This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…
Suppose we are given two metric spaces and a family of continuous transformations from one to the other. Given a probability distribution on each of these two spaces - namely the source and the target measures - the Wasserstein alignment…