Adversarial Attacks

AbstractNeural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data …...

AbstractWe address the problem of adversarial attacks on text classification, which is rarely studied comparing to attacks on image classification. The challenge of this task is to generate adversarial examples …...

AbstractNeural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of these systems—fathoming how and when neural-based systems fail …...

AbstractAdversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based …...

AbstractRecent high scores on pronoun translation using context-aware neural machine translation have suggested that current approaches work well. ContraPro is a notable example of a contrastive challenge set for English→German …...

AbstractAdversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans. Natural Language Processing (NLP) has mostly focused on high-level attack scenarios such …...

AbstractAdversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a …...

AbstractTo increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show …...

AbstractAdversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can …...

AbstractAdversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change …...

Previous work on adversarial attacks on depen- dency parsers has mostly focused on attack methods, as opposed to the quality of adver- sarial examples, which in previous work has been …...

Pretrained language models (PLMs) perform poorly under adversarial attacks. To im- prove the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adver- …...

AbstractMultilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when …...

AbstractResearch shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs …...

AbstractRecently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP). A central research topic has been the investigation of search algorithms and search …...

AbstractWe evaluate neural model robustness to adversarial attacks using different types of linguistic unit perturbations – character and word, and propose a new method for strategic sentence-level perturbations. We experiment …...

AbstractRecent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show that adversarial …...

AbstractAdversarial 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 …...

AbstractSemantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against …...

AbstractDeep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can …...

AbstractAdversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research …...

AbstractSocial media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment, we …...

AbstractStudies show machine translation systems are vulnerable to adversarial attacks, where a small change to the input produces an undesirable change in system behavior. This work considers whether this vulnerability …...

AbstractWarning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of …...

AbstractLarge-scale pretrained language models have achieved SOTA results on NLP tasks. However, they have been shown vulnerable to adversarial attacks especially for logographic languages like Chinese. In this work, we …...

AbstractHuman evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and …...

AbstractNatural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks – malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. …...

AbstractMany adversarial attacks in NLP perturb text in puts to produce visually similar strings (‘ergo’, ‘εrgo’) which are legible to humans but degrade model performance. Although preserving legibility is a …...

AbstractAdversarial attacks on deep neural networks keep raising security concerns in natural language processing research. Existing defenses focus on improving the robustness of the victim model in the training stage. …...