Survey of Adversarial Attack, Defense and Robustness Analysis for Natural Language Processing

被引：0
作者：
Zheng H. [1 ]
Chen J. [1 ,2 ]
Zhang Y. [1 ]
Zhang X. [3 ]
Ge C. [4 ]
Liu Z. [4 ]
Ouyang Y. [5 ]
Ji S. [6 ]
机构：
[1] College of Information Engineering, Zhejiang University of Technology, Hangzhou
[2] Cyberspace Security Research Institute, Zhejiang University of Technology, Hangzhou
[3] College of Control Science and Engineering, Zhejiang University, Hangzhou
[4] College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing
[5] Nanjing Research Center, Huawei Technologies Co., Ltd., Nanjing
[6] College of Computer Science and Technology, Zhejiang University, Hangzhou
来源：
Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2021年 / 58卷 / 08期
基金：
中国国家自然科学基金;
关键词：
Adversarial attack; Deep neural network; Defense; Natural language processing; Robustness;
D O I：
10.7544/issn1000-1239.2021.20210304
中图分类号：
学科分类号：
摘要：
With the rapid development of artificial intelligence, deep neural networks have been widely applied in the fields of computer vision, signal analysis, and natural language processing. It helps machines process understand and use human language through functions such as syntax analysis, semantic analysis, and text comprehension. However, existing studies have shown that deep models are vulnerable to the attacks from adversarial texts. Adding imperceptible adversarial perturbations to normal texts, natural language processing models can make wrong predictions. To improve the robustness of the natural language processing model, defense-related researches have also developed in recent years. Based on the existing researches, we comprehensively detail related works in the field of adversarial attacks, defenses, and robustness analysis in natural language processing tasks. Specifically, we first introduce the research tasks and related natural language processing models. Then, attack and defense approaches are stated separately. The certified robustness analysis and benchmark datasets of natural language processing models are further investigated and a detailed introduction of natural language processing application platforms and toolkits is provided. Finally, we summarize the development direction of research on attacks and defenses in the future. © 2021, Science Press. All right reserved.
引用
收藏
页码：1727 / 1750
页数：23
相关论文
共 106 条
  • [91] Che Wanxiang, Li Zhenghua, Liu Ting, LTP: A Chinese language technology platform, Proc of the 23rd Int Conf on Computational Linguistics: Demonstrations, pp. 13-16, (2010)
  • [92] Qiu Xipeng, Zhang Qi, Huang Xuanjing, FudanNLP: A toolkit for Chinese natural language processing, Proc of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 49-54, (2013)
  • [93] Zhang Huaping, Miao Jun, Liu Ziyu, Et al., NLPIR-Parser: Making Chinese and English semantic analysis easier and complete, The 15es Journées Intes d'Analyse statistique des Données Textuelles, pp. 1-12, (2020)
  • [94] Bird S., NLTK: The natural language toolkit, Proc of the 21st Int Conf on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pp. 69-72, (2006)
  • [95] Wilcock G., Text annotation with OpenNLP and UIMA, Proc of the 17th Nordic Conf of Computational Linguistics, pp. 7-8, (2009)
  • [96] Yang Yuexin, Ren Gongchang, HanLP-based technology function matrix construction on Chinese process patents, International Journal of Mobile Computing and Multimedia Communications, 11, 3, pp. 48-64, (2020)
  • [97] Jiao Zhenyu, Sun Shuqi, Sun Ke, Chinese lexical analysis with deep bi-GRU-CRF network, pp. 1-10, (2018)
  • [98] Manning C, Surdeanu M, Bauer J, Et al., The stanford CoreNLP natural language processing toolkit, Proc of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55-60, (2014)
  • [99] Srinivasa-Desikan B., Natural Language Processing and Computational Linguistics: A Practical Guide to Text Analysis with Python, Gensim, spaCy, and Keras, pp. 33-48, (2018)
  • [100] Aramaki E, Yano K, Wakamiya S., MedEx/J: A one-scan simple and fast NLP tool for Japanese clinical texts, Proc of the 16th World Congress on Medical and Health Informatics, pp. 285-288, (2017)
234567891011