{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T23:39:23Z","timestamp":1775173163521,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"A*Star","award":["M21J6a0080"],"award-info":[{"award-number":["M21J6a0080"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539206","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"3603-3613","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["GradMask"],"prefix":"10.1145","author":[{"given":"Han Cheol","family":"Moon","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"given":"Shafiq","family":"Joty","sequence":"additional","affiliation":[{"name":"Nanyang Technological University & Salesforce Research, Singapore, Singapore"}]},{"given":"Xu","family":"Chi","sequence":"additional","affiliation":[{"name":"Nanyang Technological University & Singapore Institute of Manufacturing Technology, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Sid Ahmed Fezza, and Olivier D\u00e9forges","author":"Aldahdooh Ahmed","year":"2021","unstructured":"Ahmed Aldahdooh, Wassim Hamidouche, Sid Ahmed Fezza, and Olivier D\u00e9forges. 2021. Adversarial Example Detection for DNN Models: A Review."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1316"},{"key":"e_1_3_2_2_3_1","volume-title":"International Conference on Learning Representations.","author":"Ancona Marco","year":"2018","unstructured":"Marco Ancona, Enea Ceolini, Cengiz \u00d6ztireli, and Markus Gross. 2018. Towards better understanding of gradient-based attribution methods for Deep Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018.","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Nicholas Carlini, and David Wagner. 2018. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018."},{"key":"e_1_3_2_2_5_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arXiv:1607.06450 [stat.ML]"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 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). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_2_7_1","volume-title":"Towards Robustness Against Natural Language Word Substitutions. In International Conference on Learning Representations.","author":"Dong Xinshuai","year":"2021","unstructured":"Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, and Hong Liu. 2021. Towards Robustness Against Natural Language Word Substitutions. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2006"},{"key":"e_1_3_2_2_9_1","volume-title":"WordNet: An Electronic Lexical Database","author":"Fellbaum Christiane","unstructured":"Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. Bradford Books."},{"key":"e_1_3_2_2_10_1","volume-title":"Attacking Binarized Neural Networks. In International Conference on Learning Representations.","author":"Galloway Angus","year":"2018","unstructured":"Angus Galloway, Graham W. Taylor, and Medhat Moussa. 2018. Attacking Binarized Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Gan Yujian","unstructured":"Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R. Woodward, Jinxia Xie, and Pengsheng Huang. 2021. Towards Robustness of Text-to-SQL Models against Synonym Substitution. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 2505--2515."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"e_1_3_2_2_13_1","volume-title":"Jesse Vig, Zachary Taschdjian, Mohit Bansal, and Christopher R\u00e9.","author":"Goel Karan","year":"2021","unstructured":"Karan Goel, Nazneen Fatema Rajani, Jesse Vig, Zachary Taschdjian, Mohit Bansal, and Christopher R\u00e9. 2021. Robustness Gym: Unifying the NLP Evaluation Landscape. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations. Association for Computational Linguistics, Online, 42--55."},{"key":"e_1_3_2_2_14_1","volume-title":"Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations.","author":"Goodfellow Ian","year":"2015","unstructured":"Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. Proceedings of International Conference on Learning Representations (2017)."},{"key":"e_1_3_2_2_16_1","volume-title":"Deep Anomaly Detection with Outlier Exposure. In International Conference on Learning Representations.","author":"Hendrycks Dan","unstructured":"Dan Hendrycks, Mantas Mazeika, and Thomas G. Dietterich. 2019. Deep Anomaly Detection with Outlier Exposure. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_17_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Ilyas Andrew","year":"2019","unstructured":"Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry. 2019. Adversarial Examples Are Not Bugs, They Are Features. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Jia Robin","unstructured":"Robin Jia, Aditi Raghunathan, Kerem G\u00f6ksel, and Percy Liang. 2019. Certified Robustness to Adversarial Word Substitutions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 4129--4142."},{"key":"e_1_3_2_2_19_1","volume-title":"Joey Tianyi Zhou, and Peter Szolovits","author":"Jin Di","year":"2019","unstructured":"Di Jin, Zhijing Jin, Joey Tianyi Zhou, and Peter Szolovits. 2019. Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment. arXiv preprint arXiv:1907.11932 (2019)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.245"},{"key":"e_1_3_2_2_21_1","volume-title":"International Conference on Learning Representations.","author":"Krishna Kalpesh","year":"2020","unstructured":"Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, and Mohit Iyyer. 2020. Thieves on Sesame Street! Model Extraction of BERT-based APIs. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.296"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327819"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3031843.3031909"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1082"},{"key":"e_1_3_2_2_26_1","unstructured":"Jiwei Li Will Monroe and Dan Jurafsky. 2017. Understanding Neural Networks through Representation Erasure."},{"key":"e_1_3_2_2_27_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_2_30_1","volume-title":"Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension. In Findings of the Association for Computational Linguistics: EMNLP","author":"Maharana Adyasha","year":"2020","unstructured":"Adyasha Maharana and Mohit Bansal. 2020. Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics."},{"key":"e_1_3_2_2_31_1","volume-title":"Adversarial Training Methods for Semi-supervised Text Classification. In International Conference on Learning Representations.","author":"Miyato Takeru","year":"2017","unstructured":"Takeru Miyato, Andrew M Dai, and Ian Goodfellow. 2017. Adversarial Training Methods for Semi-supervised Text Classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_32_1","volume-title":"Jake Grigsby, Di Jin, and Yanjun Qi.","author":"Morris John X.","year":"2020","unstructured":"John X. Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi. 2020. TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.13"},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 142--148","author":"S\u00e9aghdha Diarmuid","year":"2016","unstructured":"Diarmuid \u00d3 S\u00e9aghdha, Blaise Thomson, , Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2016. Counter-fitting Word Vectors to Linguistic Constraints. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 142--148."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Learning Representations.","author":"Murdoch W. James","year":"2018","unstructured":"W. James Murdoch, Peter J. Liu, and Bin Yu. 2018. Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.252"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","volume":"1905","author":"Pruthi Danish","unstructured":"Danish Pruthi, Bhuwan Dhingra, and Zachary C. Lipton. 2019. Combating Adversarial Misspellings with Robust Word Recognition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Vol. abs\/1905.11268."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"e_1_3_2_2_40_1","volume-title":"Building robust natural language processing systems. Ph. D. Dissertation","author":"Robin Jia","unstructured":"Jia Robin. 2020. Building robust natural language processing systems. Ph. D. Dissertation. Stanford University, Stanford, California."},{"key":"e_1_3_2_2_41_1","volume-title":"Chandra Bhagavatula, and Yejin Choi.","author":"Sakaguchi Keisuke","year":"2019","unstructured":"Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2019. WinoGrande: An Adversarial Winograd Schema Challenge at Scale. arXiv preprint arXiv:1907.10641 (2019)."},{"key":"e_1_3_2_2_42_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter."},{"key":"e_1_3_2_2_43_1","volume-title":"Advances in Neural Information Processing Systems","author":"Sch\u00f6lkopf Bernhard","unstructured":"Bernhard Sch\u00f6lkopf, Robert C Williamson, Alex Smola, John Shawe-Taylor, and John Platt. 2000. Support Vector Method for Novelty Detection. In Advances in Neural Information Processing Systems, Vol. 12. MIT Press."},{"key":"e_1_3_2_2_44_1","volume-title":"Little","author":"Shafaei Alireza","year":"2019","unstructured":"Alireza Shafaei, Mark Schmidt, and James J. Little. 2019. A Less Biased Evaluation of Out-of-distribution Sample Detectors.. In BMVC. 3."},{"key":"e_1_3_2_2_45_1","volume-title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning. CoRR abs\/2012.15699","author":"Si Chenglei","year":"2020","unstructured":"Chenglei Si, Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Qun Liu, and Maosong Sun. 2020. Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning. CoRR abs\/2012.15699 (2020)."},{"key":"e_1_3_2_2_46_1","volume-title":"2nd International Conference on Learning Representations, ICLR","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan, A. Vedaldi, and Andrew Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Workshop Track Proceedings."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Seattle, Washington, USA, 1631--1642."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning -","volume":"70","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (Sydney, NSW, Australia) (ICML'17). JMLR.org, 3319--3328."},{"key":"e_1_3_2_2_50_1","volume-title":"International Conference on Learning Representations.","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.321"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.263"},{"key":"e_1_3_2_2_53_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc., 5998--6008."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Eric Wallace Shi Feng Nikhil Kandpal Matt Gardner and Sameer Singh. 2019. Universal Adversarial Triggers for Attacking and Analyzing NLP. In Empirical Methods in Natural Language Processing.","DOI":"10.18653\/v1\/D19-1221"},{"key":"e_1_3_2_2_55_1","volume-title":"Proceedings of the 2021 Conference of the North American","author":"Wang Wenjie","unstructured":"Wenjie Wang, Pengfei Tang, Jian Lou, and Li Xiong. 2021. Certified Robustness to Word Substitution Attack with Differential Privacy. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 1102--1112."},{"key":"e_1_3_2_2_56_1","volume-title":"Natural Language Adversarial Attacks and Defenses in Word Level. CoRR","author":"Wang Xiaosen","year":"2019","unstructured":"Xiaosen Wang, Hao Jin, and Kun He. 2019. Natural Language Adversarial Attacks and Defenses in Word Level. CoRR (2019)."},{"key":"e_1_3_2_2_57_1","volume-title":"Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks. CoRR abs\/2008.03709","author":"Wang Xiaosen","year":"2020","unstructured":"Xiaosen Wang, Yichen Yang, Yihe Deng, and Kun He. 2020. Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks. CoRR abs\/2008.03709 (2020)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_2_59_1","volume-title":"Robert Stanforth, Vivek Natarajan, Joseph R. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Simon Kohl, Taylan Cemgil, S. M. Ali Eslami, and Olaf Ronneberger.","author":"Winkens Jim","year":"2020","unstructured":"Jim Winkens, Rudy Bunel, Abhijit Guha Roy, Robert Stanforth, Vivek Natarajan, Joseph R. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Simon Kohl, Taylan Cemgil, S. M. Ali Eslami, and Olaf Ronneberger. 2020. Contrastive Training for Improved Out-of-Distribution Detection."},{"key":"e_1_3_2_2_60_1","volume-title":"Findings of the Association for Computational Linguistics: EMNLP","author":"Yong Yoo Jin","year":"2021","unstructured":"Yoo Jin Yong and Qi Yanjun. 2021. Towards Improving Adversarial Training of NLP Models. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, 945--956."},{"key":"e_1_3_2_2_61_1","volume-title":"Zeiler and Rob Fergus","author":"Matthew","year":"2014","unstructured":"Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. In Computer Vision -- ECCV 2014. Springer International Publishing, Cham, 818--833."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3374217"},{"key":"e_1_3_2_2_63_1","unstructured":"Wei Emma Zhang Quan Z. Sheng and Ahoud Abdulrahmn F. Alhazmi. 2020. Generating Textual Adversarial Examples for Deep Learning Models: A Survey. ACM Trans. Intell. Syst. Technol. (2020)."},{"key":"e_1_3_2_2_64_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. In Advances in Neural Information Processing Systems, Vol. 28. Curran Associates, Inc., 649--657."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"crossref","unstructured":"Yinhe Zheng Guanyi Chen and Minlie Huang. 2020. Out-of-domain Detection for Natural Language Understanding in Dialog Systems.","DOI":"10.1109\/TASLP.2020.2983593"},{"key":"e_1_3_2_2_66_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Zhou Yichao","unstructured":"Yichao Zhou, Jyun-Yu Jiang, Kai-Wei Chang, and Wei Wang. 2019. Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 4904--4913."},{"key":"e_1_3_2_2_67_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Zhou Yi","unstructured":"Yi Zhou, Xiaoqing Zheng, Cho-Jui Hsieh, Kai-Wei Chang, and Xuanjing Huang. 2021. Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 5482--5492."},{"key":"e_1_3_2_2_68_1","volume-title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In International Conference on Learning Representations.","author":"Zhu Chen","year":"2020","unstructured":"Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, and Jingjing Liu. 2020. FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In International Conference on Learning Representations."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539206","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:59:58Z","timestamp":1750186798000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539206"}},"subtitle":["Gradient-Guided Token Masking for Textual Adversarial Example Detection"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":68,"alternative-id":["10.1145\/3534678.3539206","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539206","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}