Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in Chinese, such methods are not applicable since words in Chinese require segmentations first. In this paper, we propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers. Experiments results show that the generated adversarial samples can mislead strong target models and remain fluent and semantically preserved.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingSentenceSimilar Papers 제목 키워드 기반
Towards a Robust Deep Neural Network in Texts: A Survey
Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based…
General Classificationimage-classificationImage Classificationspeech-recognition+2Identify Bilingual Patterns and Phrases from a Bilingual Sentence Pair
This paper presents a method for automatically identifying bilingual grammar patterns and extracting bilingual phrase instances from a given English-Chinese sentence pair. In our approach, the English-Chinese sentence pa…
Machine TranslationSentenceTranslationR&R: Metric-guided Adversarial Sentence Generation
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences t…
Adversarial AttackGeneral ClassificationSemantic SimilaritySemantic Textual Similarity+4MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences
Chinese meme-face is a special kind of internet subculture widely spread in Chinese Social Community Networks. It usually consists of a template image modified by some amusing details and a text caption. In this paper, w…
Face GenerationGenerative Adversarial NetworkDuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
In this paper, we focus on studying robustness evaluation of Chinese question matching. Most of the previous work on analyzing robustness issue focus on just one or a few types of artificial adversarial examples. Instead…
Natural Questions