应用量子行为粒子群优化算法的文本对抗

doi:10.3778/j.issn.1002-8331.2011-0168

摘要/Abstract

摘要： 文本对抗攻击能够极大地弱化深度神经网络在自然语言处理任务中的判别能力，对抗攻击方法的研究是提升深度神经网络鲁棒性的重要方法。现有的词级别文本对抗方法在搜索对抗样本时不够有效，搜索到的往往不是最理想的样本。针对这一缺陷，提出了基于改进的量子行为粒子群优化算法的文本对抗方法。通过对量子行为粒子群优化算法进行离散化的适应性改动，更有效地搜索出高质量的对抗样本。实验结果表明，提出的方法在多个数据集上取得了更高的攻击成功率，同时保持了更低的改动率，人工评测则表明提出的方法生成的对抗样本相比于其他对抗样本能够更多地保留语法和语义的正确性。

关键词: 文本对抗攻击, 量子行为粒子群优化算法, 自然语言处理

Abstract: Deep neural networks have been proved to be vulnerable to adversarial attacks, and research on adversarial attacks is an important method to improve the robustness of deep neural networks. The existing word level adversarial attack methods for texts are not effective enough, and always generate adversarial examples which are not the ideal ones. To solve this problem, an attack method which employs improved quantum behaved particle swarm optimization（QPSO） algorithm is proposed. By modifying QPSO to adapt the discreteness, high quality adversarial examples can be searched more effectively. The experiment results show that the proposed method can achieve higher attack success rates and lower modification rates on multiple datasets. The human evaluation shows that adversarial examples generated by the proposed method can retain more grammatical and semantic correctness than other adversarial examples.

Key words: text adversarial attack, quantum behaved particle swarm optimization, natural language processing

徐尹翔, 陈祺东, 孙俊. 应用量子行为粒子群优化算法的文本对抗[J]. 计算机工程与应用, 2022, 58(9): 175-180.

XU Yinxiang, CHEN Qidong, SUN Jun. Text Adversarial Attack Method Applying Based on Improved Quantum Behaved Particle Swarm Optimization[J]. Computer Engineering and Applications, 2022, 58(9): 175-180.

参考文献

[1] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[2] OORD A V D，DIELEMAN S，ZEN H，et al.WaveNet：a generative model for raw audio[J].arXiv：1609.03499，2016.
[3] DONG L，WEI F，TAN C，et al.Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics（Volume 2：Short Papers），2014：49-54.
[4] SZEGEDY C，ZAREMBA W，SUTSKEVER I，et al.Intriguing properties of neural network[C]//Proceedings of the 2nd International Conference on Learning Representations，2014.
[5] GOODFELLOW I J，SHLENS J，SZEGEDY C.Explaining and harnessing adversarial examples[C]//Proceedings of the 2nd International Conference on Learning Representations，2014.
[6] LIU A，LIU X，FAN J，et al.Perceptual-sensitive gan for generating adversarial patches[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：1028-1035.
[7] WANG X，JIN H，HE K.Natural language adversarial attacks and defenses in word level[J].arXiv：1909.06723，2019.
[8] MA J，GAO W，MITRA P，et al.Detecting rumors from microblogs with recurrent neural networks[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence，2016：3818-3824.
[9] EBRAHIMI J，LOWD D，DOU D.On adversarial examples for character-level neural machine translation[C]//Proceedings of the 27th International Conference on Computational Linguistics，2018：653-663.
[10] BELINKOV Y，BISK Y.Synthetic and natural noise both break neural machine translation[C]//Proceedings of the 6th International Conference on Learning Representations，2018.
[11] HOSSEINI H，KANNAN S，ZHANG B，et al.Deceiving google’s perspective API built for detecting toxic comments[J].arXiv：1702.08138，2017.
[12] PRUTHI D，DHINGRA B，LIPTON Z C.Combating adversarial misspellings with robust word recognition[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，2019：5582-5591.
[13] JIA R，LIANG P.Adversarial examples for evaluating reading comprehension systems[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing，2017：2021-2031.
[14] WANG Y，BANSAL M.Robust machine comprehension models via adversarial training[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，Volume 2（Short Papers），2018：575-581.
[15] IYYER M，WIETING J，GIMPEL K，et al.Adversarial example generation with syntactically controlled paraphrase networks[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，Volume 1（Long Papers），2018：1875-1885.
[16] ZHAO Z，DUA D，SINGH S.Generating natural adversarial examples[C]//Proceedings of the 6th International Conference on Learning Representations，2018.
[17] PAPERNOT N，MCDANIEL P，SWAMI A，et al.Crafting adversarial input sequences for recurrent neural networks[C]//Proceedings of the IEEE Military Communications Conference，2016：49-54.
[18] SAMANTA S，MEHTA S.Towards crafting text adversarial samples[J].arXiv：1707.02812，2017.
[19] REN S，DENG Y，HE K，et al.Generating natural language adversarial examples through probability weighted word saliency[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，2019：2890-2896.
[20] ALZANTOT M，SHARMA Y，ELGOHARY A，et al.Generating natural language adversarial examples[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing，2018：1085-1097.
[21] LIANG B，LI H，SU M，et al.Deep text classification can be fooled[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence，2018：4208-4215.
[22] ZANG Y，QI F，YANG C，et al.Word-level textual adversarial attacking as combinatorial optimization[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics，2020：6066-6080.
[23] DONG Z，DONG Q.Hownet and the computation of meaning[M].USA：World Scientific Publishing Co Inc，2006.
[24] KENNEDY J，EBERHART R.Particle swarm optimization[C]//Proceedings of International Conference on Neural Networks，1995：1942-1948.
[25] SUN J，XU W，FENG B.A global search strategy of quantum-behaved particle swarm optimization[C]//Proceedings of IEEE Conference on Cybernetics and Intelligent Systems，2004：111-116.
[26] MAAS A，DALY R E，PHAM P T，et al.Learning word vectors for sentiment analysis[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics：Human Language Technologies，2011：142-150.
[27] SOCHER R，PERELYGIN A，WU J，et al.Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing，2013：1631-1642.
[28] BOWMAN S R，ANGELI G，POTTS C，et al.A large annotated corpus for learning natural language inference[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing，2015：632-642.
[29] CONNEAU A，KIELA D，SCHWENK H，et al.Supervised learning of universal sentence representations from natural language inference data[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing，2017：670-680.
[30] DEVLIN J，CHANG M，LEE K，et al.Bert：pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，Volume 1（Long and Short Papers），2019：4171-4186.
[31] PENNINGTON J，SOCHER R，MANNING C D.Glove：global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，2014：1532-1543.