Related papers: Interpretable Adversarial Perturbation in Input Em…

This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task. We estimate attributions of different image regions to the decrease of the attacking cost based on the Shapley value.…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

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 $\mathcal{L}_p$…

Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow…

Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the interpretability of the learned features is a matter of concern.…

Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with…

Adversarial attacks are usually expressed in terms of a gradient-based operation on the input data and model, this results in heavy computations every time an attack is generated. In this work, we solidify the idea of representing…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…

Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…

With the abundance of large-scale deep learning models, it has become possible to repurpose pre-trained networks for new tasks. Recent works on adversarial reprogramming have shown that it is possible to repurpose neural networks for…

Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. This has been observed multiple times. Such interpretable dimensions are becoming valuable tools in different areas of…

Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio…

Recent approaches employ deep learning-based solutions for the recovery of a sharp image from its blurry observation. This paper introduces adversarial attacks against deep learning-based image deblurring methods and evaluates the…

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It involves applying gradient-based perturbation on the sentence…

Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. However, in certain scenarios, people may not…

In Natural Language Processing (NLP), pretrained language models (LMs) that are transferred to downstream tasks have been recently shown to achieve state-of-the-art results. However, standard fine-tuning can degrade the general-domain…