Download pdf
LexiGuard: Elevating NLP robustness through effortless adversarial fortification
- 1 Illinois Institute of Technology, Capitol Technology University
* Author to whom correspondence should be addressed.
Abstract
NLP models have demonstrated susceptibility to adversarial attacks, thereby compromising their robustness. Even slight modifications to input text possess the capacity to deceive NLP models, leading to inaccurate text classifications. In the present investigation, we introduce Lexi-Guard: an innovative method for Adversarial Text Generation. This approach facilitates the rapid and efficient generation of adversarial texts when supplied with initial input text. To illustrate, when targeting a sentiment classification model, the utilization of product categories as attributes is employed, ensuring that the sentiment of reviews remains unaltered. Empirical assessments were conducted on real-world NLP datasets to showcase the efficacy of our technique in producing adversarial texts that are both more semantically meaningful and exhibit greater diversity, surpassing the capabilities of numerous existing adversarial text generation methodologies. Furthermore, we leverage the generated adversarial instances to enhance models through adversarial training, demonstrating the heightened resilience of our generated attacks against model retraining endeavors and diverse model architectures.
Keywords
NLP models, NLP robustness, adversarial text generation
[1]. David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of blackbox sequence-to-sequence models. In Pro- ceedings of the 2017 Conference on Empirical Meth- ods in Natural Language Processing, pages 412– 421, Copenhagen, Denmark. Association for Com- putational Linguistics.
[2]. Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, and Kai-Wei Chang. 2018. Generating natural language adversarial ex- amples. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2890–2896, Brussels, Belgium. Association for Computational Linguistics.
[3]. Alexei Baevski and Michael Auli. 2018. Adaptive in- put representations for neural language modeling.
[4]. Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large anno- tated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics.
[5]. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: a simple approach to controlled text generation. In ICLR.
[6]. Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2018. HotFlip: White-box adversarial exam- ples for text classification. In Proceedings of the 56th Annual Meeting of the Association for Compu- tational Linguistics (Volume 2: Short Papers), pages 31–36, Melbourne, Australia. Association for Com- putational Linguistics.
[7]. Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversar- ial examples. In ICLR.
[8]. Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, and Percy Liang. 2018. Generating sentences by editing prototypes. Transactions of the Association for Computational Linguistics, 6:437–450.
[9]. Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In Proceedings of the 25th International Conference on World Wide Web, WWW ’16.
[10]. Dan Hendrycks, Xiaoyuan Liu, Eric Wallace, Adam Dziedzic, Rishabh Krishnan, and Dawn Song. 2020. Pretrained transformers improve out-of-distribution robustness. In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguis- tics.
[11]. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Toward con- trolled generation of text. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Re- search, pages 1587–1596, International Convention Centre, Sydney, Australia. PMLR.
[12]. Mohit Iyyer, John Wieting, Kevin Gimpel, and Luke Zettlemoyer. 2018. Adversarial example generation with syntactically controlled paraphrase networks. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1875–1885, New Orleans, Louisiana. Association for Computational Linguistics.
[13]. Eric Jang, Shixiang Gu, and Ben Poole. 2017. Cate- gorical reparameterization with gumbel-softmax. In ICLR.
[14]. Robin Jia and Percy Liang. 2017. Adversarial exam- ples for evaluating reading comprehension systems. In Proceedings of the 2017 Conference on Empiri- cal Methods in Natural Language Processing, pages 2021–2031, Copenhagen, Denmark. Association for Computational Linguistics.
[15]. Robin Jia, Aditi Raghunathan, Kerem Go¨ksel, and Percy Liang. 2019. Certified robustness to adver- sarial word substitutions. In Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
[16]. Di Jin, Zhijing Jin, Joey Zhou, and Peter Szolovits. 2020. Is BERT really robust? Natural language at- tack on text classification and entailment. In AAAI.
[17]. Yoon Kim. 2014. Convolutional neural net- works for sentence classification. arXiv preprint arXiv:1408.5882.
[18]. Aakanksha Naik, Abhilasha Ravichander, Norman M. Sadeh, Carolyn Penstein Rose´, and Graham Neubig. 2018. Stress test evaluation for natural language in- ference. In COLING.
[19]. Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, and Sergey Edunov. 2019. Face- book fair’s wmt19 news translation task submission. Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1).
[20]. Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2002. BLEU: a method for automatic eval- uation of machine translation. In Proc. of ACL.
[21]. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in Neural Informa- tion Processing Systems 30, pages 6830–6841.
[22]. Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, and Hongning Wang. 2019. Adversar- ial domain adaptation for machine reading compre- hension. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP).
[23]. Zhengli Zhao, Dheeru Dua, and Sameer Singh. 2018. Generating natural adversarial examples. In ICLR.
[24]. Xiang Zhou, Yixin Nie, Hao Tan, and Mohit Bansal. 2020. The curse of performance instability in analy- sis datasets: Consequences, source, and suggestions. arXiv preprint arXiv:2004.13606.
[25]. Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Thomas Goldstein, and Jingjing Liu. 2020. Freelb: En- hanced adversarial training for language understand- ing. In ICLR.
Cite this article
Omar,M. (2023). LexiGuard: Elevating NLP robustness through effortless adversarial fortification. Advances in Engineering Innovation,2,1-9.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Journal：Advances in Engineering Innovation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).