相关论文: AdvEntuRe: Adversarial Training for Textual Entail…

Gradient-based adversarial training is widely used in improving the robustness of neural networks, while it cannot be easily adapted to natural language processing tasks since the embedding space is discrete. In natural language processing…

Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…

In this paper, we propose a model using generative adversarial net (GAN) to generate realistic text. Instead of using standard GAN, we combine variational autoencoder (VAE) with generative adversarial net. The use of high-level latent…

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while…

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Adversarial examples reveal the vulnerability and unexplained nature of neural networks. Studying the defense of adversarial examples is of considerable practical importance. Most adversarial examples that misclassify networks are often…

We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. Unlike prior self-supervised approaches which often involve geometric augmentations on the image…

Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a…

Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and…

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

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…

The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE)…

While most image captioning aims to generate objective descriptions of images, the last few years have seen work on generating visually grounded image captions which have a specific style (e.g., incorporating positive or negative…

In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the most successful methods. To deal with both the robustness…

Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

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…