Related papers: Gradient-Based Word Substitution for Obstinate Adv…
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…
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven by local heuristic…
Text style transfer is a challenging text generation problem, which aims at altering the style of a given sentence to a target one while keeping its content unchanged. Since there is a natural scarcity of parallel datasets, recent works…
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…
Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the…
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial…
While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue. In this paper we…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…
Attacks on deep learning models are often difficult to identify and therefore are difficult to protect against. This problem is exacerbated by the use of public datasets that typically are not manually inspected before use. In this paper,…
Generating challenging instances is crucial for the evaluation and advancement of combinatorial optimization solvers. In this work, we introduce EALG (Evolutionary Adversarial Generation of Language Model-Guided Generators), a novel…
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of…
Despite advancements in Natural Language Processing (NLP), models remain vulnerable to adversarial attacks, such as synonym substitutions. While prior work has focused on improving robustness for feed-forward and convolutional…
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…
Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good…
Various techniques are used in the generation of adversarial examples, including methods such as TextBugger which introduce minor, hardly visible perturbations to words leading to changes in model behaviour. Another class of techniques…
Neural retrieval models have acquired significant effectiveness gains over the last few years compared to term-based methods. Nevertheless, those models may be brittle when faced to typos, distribution shifts or vulnerable to malicious…
Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…
Adversarial examples are a hot topic due to their abilities to fool a classifier's prediction. There are two strategies to create such examples, one uses the attacked classifier's gradients, while the other only requires access to the…
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction. However, a potential pitfall for this approach is…
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has…