ABSTRACT
Deep learning is widely used in many kinds of network applications, but errors in texts challenge the model's performance. In order to study the impact of erroneous knowledge on the Chinese text classification model, in this paper we propose a word-level black box adversarial example generation method called WordErrorSim. The algorithm uses SIGHAN Back-off 2013 and ZDIC to construct erroneous knowledge space. The adversarial examples generate by replacing character with pronounce similar character, shape similar character or other commonly used erroneous character. The adversarial example can achieve the attack without changing the semantic or grammar of the original sentence. Besides, we design and implement Chinese Pronunciation-Shape Similarity (CPSS) algorithm to measure the change between the adversarial example and the original text. We verify the effectiveness of the proposed method with real dataset on Bi-LSTM and TextCNN models. The experiment results show that our method can significantly reduce the classification accuracy of the model.
- Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of 3rd International Conference on Learning Representations (ICLR 2015) . ICLR, San Diego, CA, United states.Google Scholar
- Alexey Kurakin, Ian J. Goodfellow, and Samy Bengio. 2017. Adversarial examples in the physical world. In Proceedings of 5th International Conference on Learning Representations (ICLR 2017) . ICLR, Toulon, France.Google Scholar
- Suranjana Samanta, and Sameep Mehta. 2017. Towards crafting text adversarial samples. arXiv:1707.02812.Google Scholar
- Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani B. Srivastava, and Kai-Wei Chang. 2018. Generating natural language adversarial examples. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) . ACL, Brussels, Belgium, 2890-2896.Google ScholarCross Ref
- Matt J. Kusner, Yu Sun, Nicholas I. Kolkin, and Kilian Q. Weinberger. 2015. From word embeddings to document distances. In Proceedings of 32nd International Conference on Machine Learning (ICML 2015) . International Machine Learning Society, Lile, France, 957-966.Google Scholar
- Wenqi Wang, Run Wang, Lina Wang, and Benxiao Tang. 2019. Adversarial examples generation approach for tendency classification on Chinese texts. Ruan Jian Xue Bao/Journal of Software, 2019, 30(8):2415−2427 (in Chinese). http://www.jos.org.cn/1000-9825/5765.htmGoogle Scholar
- Xin Tong, Luona Wang, Runzheng Wang, and Jingya Wang. 2020. A Generation Method of Word-level Adversarial Samples for Chinese Text Classification. Netinfo Security, 2020, 20(9): 12-16.Google Scholar
- Nuo Cheng, G. Chang, H. Gao, G. Pei and Y. Zhang. 2020. WordChange: Adversarial Examples Generation Approach for Chinese Text Classification. IEEE Access, 2020, 8:79561-79572. https://doi.org/10.1109/ACCESS.2020.2988786.Google ScholarCross Ref
- C.-L. Liu, M.-H. Lai, K.-W. Tien, Y.-H. Chuang, S.-H. Wu, and C.-Y. Lee. 2011. Visually and Phonologically Similar Characters in Incorrect Chinese Words: Analyses, Identification, and Applications. ACM Transactions on Asian Language Information Processing 10, 2, Article 10 (June 2011), 39 pages. https://doi.org/10.1145/1967293.1967297Google ScholarDigital Library
- Chao-Lin Liu, Kan-Wen Tien, Yi-Hsuan Chuang, Chih-Bin Huang, and Juei-Yu Weng. 2009. Two applications of lexical information to computer-assisted item authoring for elementary chinese. In Proceedings of 22nd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE 2009) . Springer Verlag, Tainan, Taiwan, 470-480. https://doi.org/10.1007/978-3-642-02568-6_48Google ScholarDigital Library
- Shih-Hung Wu, Chao-Lin Liu, and Lung-Hao Lee. 2013. Chinese Spelling Check Evaluation at SIGHAN Bake-off 2013. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing (SIGHAN'13) . ACL, Nagoya, Japan, 35-42.Google Scholar
- Shengjun Liu, Ningkang Jiang, and Yuanbin Wu. 2020. Visual Attack and Defense on Text. arXiv:2008.10356.Google Scholar
- Alexis Conneau, Douwe Kiela, Holger Schwenk, Loic Barrault, and Antoine Bordes. 2017. Supervised learning of universal sentence representations from natural language inference. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2017) . ACL, Copenhagen, Denmark, 670-680.Google ScholarCross Ref
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014) . ACL, Doha, Qatar, 1746-1751.Google ScholarCross Ref
- Ji Gao, Jack Lanchantin, Mary Lou Soffa, and Yanjun Qi. 2018. Black-box generation of adversarial text sequences to evade deep learning classifiers. In Proceedings of the 2018 IEEE Symposium on Security and Privacy Workshops (SPW 2018) . IEEE, San Francisco, CA, 50-56. https://doi.org/10.1109/SPW.2018.00016Google ScholarCross Ref
Recommendations
Chinese adversarial examples generation approach with multi-strategy based on semantic
AbstractRecent studies have shown that after adding small perturbations that are imperceptible to humans, deep neural networks (DNNs) with good performance and popular application are likely to produce incorrect results. These processed samples are called ...
A hybrid adversarial training for deep learning model and denoising network resistant to adversarial examples
AbstractDeep neural networks (DNNs) are vulnerable to adversarial attacks that generate adversarial examples by adding small perturbations to the clean images. To combat adversarial attacks, the two main defense methods used are denoising and adversarial ...
Feature autoencoder for detecting adversarial examples
AbstractDeep neural networks (DNNs) have gained widespread adoption in computer vision. Unfortunately, state‐of‐the‐art DNNs are vulnerable to adversarial example (AE) attacks, where an adversary introduces imperceptible perturbations to a test example ...
Comments