A Context Aware Approach for Generating Natural Language Attacks
We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed attack finds candidate words by considering the information of both the original word and its surrounding context. It jointly leverages masked language modelling and next sentence prediction for context understanding. In comparison to attacks proposed in prior literature, we are able to generate high quality adversarial examples that do significantly better both in terms of success rate and word perturbation percentage.
Code (1)
Tasks
Language ModellingSentencetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Zero-Query Transfer Attacks on Context-Aware Object Detectors
Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a conte…
Adversarial AttackObjectDefending Against Backdoor Attacks in Natural Language Generation
The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately…
Backdoor AttackDialogue GenerationMachine TranslationText Generation+1Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
While adversarial attacks on vision-and-language pretraining (VLP) models have been explored, generating natural adversarial samples crafted through realistic and semantically meaningful perturbations remains an open cha…
Image CaptioningQuestion AnsweringVisual Question AnsweringSSCAE: A Novel Semantic, Syntactic, and Context-Aware Natural Language Adversarial Example Generator
Training a machine learning model with adversarial examples (AEs) improves its robustness against adversarial attacks. Hence, it is crucial to develop effective generative models to produce high-quality AEs. Developing s…
Adversarial AttackGenerating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natur…
DecoderReview GenerationSentenceText Generation