Related papers: Cross Domain Regularization for Neural Ranking Mod…

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…

Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on…

In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Researchers hope that models trained on these more challenging datasets will rely…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is…

The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, we have yet to…

With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…

Open set domain adaptation refers to the scenario that the target domain contains categories that do not exist in the source domain. It is a more common situation in the reality compared with the typical closed set domain adaptation where…

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations,…

Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness against those adversarial attacks but hurts generalization of…

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial training, a heuristic form of robust optimization that…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…

Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input, e.g. adversarial noise leading to erroneous decisions. We…

It has been consistently reported that many machine learning models are susceptible to adversarial attacks i.e., small additive adversarial perturbations applied to data points can cause misclassification. Adversarial training using…

Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and…