Abstract
Adversarial examples have received increasing attention recently due to their significant values in evaluating and improving the robustness of deep neural networks. Existing adversarial attack algorithms have achieved good result for most images. However, those algorithms cannot be directly applied to texts as the text data is discrete in nature. In this paper, we extend two state-of-the-art attack algorithms, PGD and C&W, to craft adversarial text examples for RNN-based models. For Extend-PGD attack, it identifies the words that are important for classification by computing the Jacobian matrix of the classifier, to effectively generate adversarial text examples. For Extend-C&W attack, it utilizes \(\mathcal {L}_{1}\) regularization to minimize the alteration of the original input text. We conduct comparison experiments on two recurrent neural networks trained for classifying texts in two real-world datasets. Experimental results show that our Extend-PGD and Extend-C&W attack algorithms have advantages of attack success rate and semantics-preserving ability, respectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: IEEE Symposium on Security and Privacy, pp. 39–57 (2017)
Gao, J., Lanchantin, J., Soffa, M.L., Qi, Y.: Black-box generation of adversarial text sequences to evade deep learning classifiers. In: IEEE Symposium on Security and Privacy Workshops, pp. 50–56 (2018)
Gong, Z., Wang, W., Li, B., Song, D., Ku, W.S.: Adversarial texts with gradient methods. arXiv:1801.07175 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015)
Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764–1772 (2014)
Hochreiter, S., Schmolze, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Li, J., Ji, S., Du, T., Li, B., Wang, T.: TextBugger: generating adversarial text against real-world applications. In: Network and Distributed System Security Symposium (2018)
Liang, B., Li, H., Su, M., Bian, P., Li, X., Shi, W.: Deep text classification can be fooled. In: IJCAI, pp. 4208–4215 (2018)
Liu, S., Yang, N., Li, M., Zhou, M.: A recursive recurrent neural network for statistical machine translation. In: ACL, pp. 1491–1500 (2014)
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: ACL, pp. 142–150 (2011)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR (2018)
Mesnil, G., Mikolov, T., Ranzato, M.A., Bengio, Y.: Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews. In: ICLR (2015)
Metsis, V., Androutsopoulos, I., Paliouras, G.: Spam fitering with naive bayes-which naive bayes? CEAS 17, 28–69 (2006)
Moosavi-Dezfooli, S., Fawzi, A., Frossard, P.: DeepFool: a simple and accurate method to fool deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016)
Pagliardini, M., Gupta, P., Jaggi, M.: Unsupervised learning of sentence embeddings using compositional n-gram features. In: NAACL: Human Language Technologies, pp. 528–540 (2018)
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Empirical Methods in Natural Language Processing (2014)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Cogn. Model. 14(2) (1988)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv:1312.6199 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, C., Lin, W., Yang, Z. (2020). Generating Adversarial Texts for Recurrent Neural Networks. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)