Related papers: Domain Adversarial Training: A Game Perspective
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore…
High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning algorithms with…
We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distribution used to train the system. This problem of robustness to DS…
In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard…
Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…
Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is…
Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain. Inspiring results have been acquired by learning domain-invariant deep features via…
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…
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of…
Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial training and its variants have been shown to be the most…
Learning solution operators for differential equations with neural networks has shown great potential in scientific computing, but ensuring their stability under input perturbations remains a critical challenge. This paper presents a robust…
Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods…
Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and…
Deep neural networks (DNNs) are vulnerable to adversarial examples obtained by adding small perturbations to original examples. The added perturbations in existing attacks are mainly determined by the gradient of the loss function with…
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…