Related papers: Interpretable Adversarial Training for Text
Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages. Current unsupervised…
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distribution to describe the desired properties of the learned…
Optimization algorithms are pivotal in advancing various scientific and industrial fields but often encounter obstacles such as trapping in local minima, saddle points, and plateaus (flat regions), which makes the convergence to reasonable…
Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate adversarial examples by leveraging the $\mathcal{L}_p$…
Recent work has shown that additive threat models, which only permit the addition of bounded noise to the pixels of an image, are insufficient for fully capturing the space of imperceivable adversarial examples. For example, small rotations…
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy…
Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a…
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks…
Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…
Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…
Fine-grained word meaning resolution remains a critical challenge for neural language models (NLMs) as they often overfit to global sentence representations, failing to capture local semantic details. We propose a novel adversarial training…
Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…
Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes…
Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain, where data privacy and acquisition cost constraints often…
We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally.…
We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…
Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…
Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are…
Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…