Related papers: BERT is Robust! A Case Against Synonym-Based Adver…
Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training. However, recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence…
Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…
Despite excellent performance on many tasks, NLP systems are easily fooled by small adversarial perturbations of inputs. Existing procedures to defend against such perturbations are either (i) heuristic in nature and susceptible to stronger…
Artificial neural networks in general and deep learning networks in particular established themselves as popular and powerful machine learning algorithms. While the often tremendous sizes of these networks are beneficial when solving…
Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural…
Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…
In this paper we present a set of experiments carried out with BERT on a number of Italian sentences taken from poetry domain. The experiments are organized on the hypothesis of a very high level of difficulty in predictability at the three…
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…
Much information available to applied researchers is contained within written language or spoken text. Deep language models such as BERT have achieved unprecedented success in many applications of computational linguistics. However, much…
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…
Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…
Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the exponentially large…
Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…
Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…
This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Specifically, we fine-tuned BERT and XLNet, two bidirectional…
Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the…
Language models like BERT excel at sentence classification tasks due to extensive pre-training on general data, but their robustness to parameter corruption is unexplored. To understand this better, we look at what happens if a language…
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a…
This paper proposes a strategy to assess the robustness of different machine learning models that involve natural language processing (NLP). The overall approach relies upon a Search and Semantically Replace strategy that consists of two…