相关论文: Adversarial Training for Commonsense Inference

The field of adversarial robustness has attracted significant attention in machine learning. Contrary to the common approach of training models that are accurate in average case, it aims at training models that are accurate for worst case…

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Machine learning models are often trained on data from one distribution and deployed on others. So it becomes important to design models that are robust to distribution shifts. Most of the existing work focuses on optimizing for either…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to…

Contrastive learning (CL) has recently been applied to adversarial learning tasks. Such practice considers adversarial samples as additional positive views of an instance, and by maximizing their agreements with each other, yields better…

Adversarial examples are carefully crafted attack points that are supposed to fool machine learning classifiers. In the last years, the field of adversarial machine learning, especially the study of perturbation-based adversarial examples,…

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to train a large pretrained language model on a specific dataset.…

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification…

Machine learning models are increasingly used in critical applications but are mostly "black boxes" due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex…

An adversarial process between two deep neural networks is a promising approach to train a robust model. In this paper, we propose an adversarial process using cosine similarity, whereas conventional adversarial processes are based on…

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations…

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expensive min-max problems that limit their application in…

We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model…

Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often…

Pre-trained language models (PTLMs) have achieved impressive performance on commonsense inference benchmarks, but their ability to employ commonsense to make robust inferences, which is crucial for effective communications with humans, is…