{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T21:59:18Z","timestamp":1773957558794,"version":"3.50.1"},"reference-count":94,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2024,9,18]]},"abstract":"<jats:p>Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a distinct configuration of four components: a goal function, allowable transformations, a search method, and constraints. In this survey, we systematically present the different components used throughout the literature, using an attack-independent framework which allows for easy comparison and categorisation of components. Our work aims to serve as a comprehensive guide for newcomers to the field and to spark targeted research into refining the individual attack components.<\/jats:p>","DOI":"10.3233\/aic-230279","type":"journal-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T17:56:41Z","timestamp":1712080601000},"page":"655-676","source":"Crossref","is-referenced-by-count":6,"title":["Token-modification adversarial attacks for natural language processing: A survey"],"prefix":"10.1177","volume":"37","author":[{"given":"Tom","family":"Roth","sequence":"first","affiliation":[{"name":"University of Technology Sydney, NSW, Australia"},{"name":"CSIRO\u2019s Data61, Sydney, NSW, Australia"}]},{"given":"Yansong","family":"Gao","sequence":"additional","affiliation":[{"name":"CSIRO\u2019s Data61, Sydney, NSW, Australia"}]},{"given":"Alsharif","family":"Abuadbba","sequence":"additional","affiliation":[{"name":"CSIRO\u2019s Data61, Sydney, NSW, Australia"}]},{"given":"Surya","family":"Nepal","sequence":"additional","affiliation":[{"name":"CSIRO\u2019s Data61, Sydney, NSW, Australia"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, NSW, Australia"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-230279_ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105210"},{"key":"10.3233\/AIC-230279_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1316"},{"key":"10.3233\/AIC-230279_ref3","unstructured":"Y.\u00a0Belinkov and Y.\u00a0Bisk, Synthetic and natural noise both break neural machine translation, in: 6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings, OpenReview.net, 2018. https:\/\/openreview.net\/forum?id=BJ8vJebC."},{"key":"10.3233\/AIC-230279_ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.647"},{"key":"10.3233\/AIC-230279_ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833641"},{"key":"10.3233\/AIC-230279_ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.382"},{"key":"10.3233\/AIC-230279_ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"10.3233\/AIC-230279_ref8","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.neucom.2023.01.071","article-title":"TextGuise: Adaptive adversarial example attacks on text classification model","volume":"529","author":"Chang","year":"2023","journal-title":"Neurocomputing"},{"key":"10.3233\/AIC-230279_ref9","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"10.3233\/AIC-230279_ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3283308","article-title":"A word-level adversarial attack method based on sememes and an improved quantum-behaved particle swarm optimization","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"04","key":"10.3233\/AIC-230279_ref11","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1609\/aaai.v34i04.5767","article-title":"Seq2Sick: Evaluating the robustness of sequence-to-sequence models with adversarial examples","volume":"34","author":"Cheng","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/AIC-230279_ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.753"},{"key":"10.3233\/AIC-230279_ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.3233\/AIC-230279_ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474369.3486871"},{"key":"10.3233\/AIC-230279_ref15","unstructured":"Z.\u00a0Dong, Q.\u00a0Dong and C.\u00a0Hao, HowNet and its computation of meaning, in: Coling 2010: Demonstrations, Coling 2010 Organizing Committee, Beijing, China, 2010, pp.\u00a053\u201356. https:\/\/www.aclweb.org\/anthology\/C10-3014."},{"key":"10.3233\/AIC-230279_ref16","unstructured":"J.\u00a0Ebrahimi, D.\u00a0Lowd and D.\u00a0Dou, On adversarial examples for character-level neural machine translation, in: Proceedings of the 27th International Conference on Computational Linguistics, Association for Computational Linguistics, Santa Fe, New Mexico, USA, 2018, pp.\u00a0653\u2013663. https:\/\/www.aclweb.org\/anthology\/C18-1055."},{"key":"10.3233\/AIC-230279_ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2006"},{"key":"10.3233\/AIC-230279_ref18","unstructured":"S.\u00a0Eger and Y.\u00a0Benz, From hero to z\u00e9roe: A benchmark of low-level adversarial attacks, in: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, AACL\/IJCNLP 2020, Suzhou, China, December 4\u20137, 2020, K.\u00a0Wong, K.\u00a0Knight and H.\u00a0Wu, eds, Association for Computational Linguistics, 2020, pp.\u00a0786\u2013803. https:\/\/aclanthology.org\/2020.aacl-main.79."},{"key":"10.3233\/AIC-230279_ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1165"},{"key":"10.3233\/AIC-230279_ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.616"},{"key":"10.3233\/AIC-230279_ref21","doi-asserted-by":"crossref","unstructured":"C.\u00a0Emmery, \u00c1.\u00a0K\u00e1d\u00e1r and G.\u00a0Chrupala, Adversarial stylometry in the wild: Transferable lexical substitution attacks on author profiling, in: EACL, 2021, pp.\u00a02388\u20132402. https:\/\/www.aclweb.org\/anthology\/2021.eacl-main.203\/.","DOI":"10.18653\/v1\/2021.eacl-main.203"},{"key":"10.3233\/AIC-230279_ref22","doi-asserted-by":"crossref","unstructured":"C.\u00a0Fellbaum, WordNet: An Electronic Lexical Database, Bradford Books, 1998.","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"10.3233\/AIC-230279_ref23","doi-asserted-by":"crossref","unstructured":"B.\u00a0Formento, C.S.\u00a0Foo, L.A.\u00a0Tuan and S.K.\u00a0Ng, Using punctuation as an adversarial attack on deep learning-based NLP systems: An\u00a0empirical study, in: Findings of the Association for Computational Linguistics: EACL 2023, Association for Computational Linguistics, Dubrovnik, Croatia, 2023, 1\u201334. https:\/\/aclanthology.org\/2023.findings-eacl.1.","DOI":"10.18653\/v1\/2023.findings-eacl.1"},{"key":"10.3233\/AIC-230279_ref24","doi-asserted-by":"crossref","unstructured":"P.\u00a0Gai\u0144ski and K.\u00a0Ba\u0142azy, Step by step loss goes very far: Multi-step quantization for adversarial text attacks, in: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Dubrovnik, Croatia, 2023, pp.\u00a02038\u20132048. https:\/\/aclanthology.org\/2023.eacl-main.149.","DOI":"10.18653\/v1\/2023.eacl-main.149"},{"key":"10.3233\/AIC-230279_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00016"},{"key":"10.3233\/AIC-230279_ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"10.3233\/AIC-230279_ref28","unstructured":"I.J.\u00a0Goodfellow, J.\u00a0Shlens and C.\u00a0Szegedy, Explaining and harnessing adversarial examples, in: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings, Y.\u00a0Bengio and Y.\u00a0LeCun, eds, 2015, http:\/\/arxiv.org\/abs\/1412.6572."},{"key":"10.3233\/AIC-230279_ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15919-0_17"},{"key":"10.3233\/AIC-230279_ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.182"},{"key":"10.3233\/AIC-230279_ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-srw.16"},{"key":"10.3233\/AIC-230279_ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1147"},{"key":"10.3233\/AIC-230279_ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.164"},{"key":"10.3233\/AIC-230279_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"issue":"05","key":"10.3233\/AIC-230279_ref36","doi-asserted-by":"publisher","first-page":"8018","DOI":"10.1609\/aaai.v34i05.6311","article-title":"Is BERT really robust? A strong baseline for natural language attack on text classification and entailment","volume":"34","author":"Jin","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/AIC-230279_ref37","unstructured":"A.\u00a0Kurakin, I.J.\u00a0Goodfellow and S.\u00a0Bengio, Adversarial machine learning at scale, in: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings, OpenReview.net, 2017. https:\/\/openreview.net\/forum?id=BJm4T4Kgx."},{"key":"10.3233\/AIC-230279_ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.232"},{"key":"10.3233\/AIC-230279_ref39","unstructured":"D.\u00a0Lee, S.\u00a0Moon, J.\u00a0Lee and H.O.\u00a0Song, Query-efficient and scalable black-box adversarial attacks on discrete sequential data via Bayesian optimization, in: International Conference on Machine Learning (ICML), 2022."},{"key":"10.3233\/AIC-230279_ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.83"},{"key":"10.3233\/AIC-230279_ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.400"},{"key":"10.3233\/AIC-230279_ref42","unstructured":"J.\u00a0Li, T.\u00a0Du, S.\u00a0Ji, R.\u00a0Zhang, Q.\u00a0Lu, M.\u00a0Yang and T.\u00a0Wang, TextShield: Robust text classification based on multimodal embedding and neural machine translation, in: 29th USENIX Security Symposium (USENIX Security 20), USENIX Association, 2020, pp.\u00a01381\u20131398. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/li-jinfeng. ISBN 978-1-939133-17-5."},{"key":"10.3233\/AIC-230279_ref43","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23138"},{"key":"10.3233\/AIC-230279_ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"10.3233\/AIC-230279_ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/585"},{"key":"10.3233\/AIC-230279_ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.trustnlp-1.24"},{"key":"10.3233\/AIC-230279_ref47","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/TASLP.2021.3130970","article-title":"Efficient combinatorial optimization for word-level adversarial textual attack","volume":"30","author":"Liu","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech and Lang. Proc."},{"key":"10.3233\/AIC-230279_ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.661"},{"key":"10.3233\/AIC-230279_ref49","doi-asserted-by":"crossref","unstructured":"R.\u00a0Maheshwary, S.\u00a0Maheshwary and V.\u00a0Pudi, Generating natural language attacks in a hard label black box setting, in: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, the Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021, AAAI Press, 2021, pp.\u00a013525\u201313533. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17595.","DOI":"10.1609\/aaai.v35i15.17595"},{"key":"10.3233\/AIC-230279_ref50","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.neunet.2022.06.018","article-title":"A universal adversarial policy for text classifiers","volume":"153","author":"Maimon","year":"2022","journal-title":"Neural Networks"},{"key":"10.3233\/AIC-230279_ref51","doi-asserted-by":"crossref","unstructured":"V.\u00a0Malik, A.\u00a0Bhat and A.\u00a0Modi, Adv-OLM: Generating Textual Adversaries via OLM, 2021.","DOI":"10.18653\/v1\/2021.eacl-main.71"},{"key":"10.3233\/AIC-230279_ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.699"},{"key":"10.3233\/AIC-230279_ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"10.3233\/AIC-230279_ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.585"},{"key":"10.3233\/AIC-230279_ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1314"},{"key":"10.3233\/AIC-230279_ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.423"},{"key":"10.3233\/AIC-230279_ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"10.3233\/AIC-230279_ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.341"},{"key":"10.3233\/AIC-230279_ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.16"},{"key":"10.3233\/AIC-230279_ref60","doi-asserted-by":"crossref","unstructured":"N.\u00a0Mrk\u0161i\u0107, D.\u00d3.\u00a0S\u00e9aghdha, B.\u00a0Thomson, M.\u00a0Ga\u0161i\u0107, L.\u00a0Rojas-Barahona, P.-H.\u00a0Su, D.\u00a0Vandyke, T.-H.\u00a0Wen and S.\u00a0Young, Counter-fitting word vectors to linguistic constraints, in: Proceedings of HLT-NAACL, 2016.","DOI":"10.18653\/v1\/N16-1018"},{"key":"10.3233\/AIC-230279_ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"10.3233\/AIC-230279_ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2016.7795300"},{"key":"10.3233\/AIC-230279_ref64","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"10.3233\/AIC-230279_ref65","doi-asserted-by":"crossref","unstructured":"J.\u00a0Pennington, R.\u00a0Socher and C.D.\u00a0Manning, GloVe: Global vectors for word representation, in: EMNLP, 2014.","DOI":"10.3115\/v1\/D14-1162"},{"issue":"140","key":"10.3233\/AIC-230279_ref66","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/AIC-230279_ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"10.3233\/AIC-230279_ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"10.3233\/AIC-230279_ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1079"},{"key":"10.3233\/AIC-230279_ref71","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TASLP.2021.3129339","article-title":"AdvExpander: Generating natural language adversarial examples by expanding text","volume":"30","author":"Shao","year":"2022","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"10.3233\/AIC-230279_ref72","unstructured":"S.\u00a0Singla, E.\u00a0Wallace, S.\u00a0Feng and S.\u00a0Feizi, Understanding impacts of high-order loss approximations and features in deep learning interpretation, in: Proceedings of the 36th International Conference on Machine Learning, K.\u00a0Chaudhuri and R.\u00a0Salakhutdinov, eds, Proceedings of Machine Learning Research, Vol.\u00a097, PMLR, 2019, pp.\u00a05848\u20135856. http:\/\/proceedings.mlr.press\/v97\/singla19a.html."},{"issue":"1","key":"10.3233\/AIC-230279_ref73","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1177\/036319908000500106","article-title":"The methodology of historical census record linkage: A user\u2019s guide to the soundex","volume":"5","author":"Stephenson","year":"1980","journal-title":"Journal of Family History"},{"key":"10.3233\/AIC-230279_ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.263"},{"issue":"0","key":"10.3233\/AIC-230279_ref75","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1162\/tacl_a_00279","article-title":"Trick me if you can: Human-in-the-loop generation of adversarial question answering examples","volume":"7","author":"Wallace","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.3233\/AIC-230279_ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.446"},{"key":"10.3233\/AIC-230279_ref77","doi-asserted-by":"crossref","unstructured":"E.\u00a0Wallace, J.\u00a0Tuyls, J.\u00a0Wang, S.\u00a0Subramanian, M.\u00a0Gardner and S.\u00a0Singh, {AllenNLP interpret}: A framework for explaining predictions of {NLP} models, in: Empirical Methods in Natural Language Processing, 2019.","DOI":"10.18653\/v1\/D19-3002"},{"key":"10.3233\/AIC-230279_ref78","unstructured":"J.\u00a0Wan, J.\u00a0Yang, S.\u00a0Ma, D.\u00a0Zhang, W.\u00a0Zhang, Y.\u00a0Yu and Z.\u00a0Li, PAEG: Phrase-level adversarial example generation for neural machine translation, in: Proceedings of the 29th International Conference on Computational Linguistics, International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 2022, pp.\u00a05085\u20135097. https:\/\/aclanthology.org\/2022.coling-1.451."},{"key":"10.3233\/AIC-230279_ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.495"},{"key":"10.3233\/AIC-230279_ref80","unstructured":"X.\u00a0Wang, H.\u00a0Jin, Y.\u00a0Yang and K.\u00a0He, Natural language adversarial defense through synonym encoding, in: Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2021, pp.\u00a0823\u2013833."},{"key":"10.3233\/AIC-230279_ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.207"},{"issue":"Database\u2013Issue","key":"10.3233\/AIC-230279_ref83","doi-asserted-by":"publisher","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: A major update to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"10.3233\/AIC-230279_ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103641"},{"key":"10.3233\/AIC-230279_ref85","unstructured":"L.\u00a0Xu, A.\u00a0Cuesta-Infante, L.\u00a0Berti-Equille and K.\u00a0Veeramachaneni, R&R: Metric-guided adversarial sentence generation, in: Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, Association for Computational Linguistics, Online Only, 2022, pp.\u00a0438\u2013452. https:\/\/aclanthology.org\/2022.findings-aacl.41."},{"key":"10.3233\/AIC-230279_ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.81"},{"key":"10.3233\/AIC-230279_ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.446"},{"key":"10.3233\/AIC-230279_ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.121"},{"key":"10.3233\/AIC-230279_ref90","unstructured":"W.\u00a0Yuan, G.\u00a0Neubig and P.\u00a0Liu, BARTScore: Evaluating generated text as text generation, in: Advances in Neural Information Processing Systems, Vol.\u00a034, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S.\u00a0Liang and J.W.\u00a0Vaughan, eds, Curran Associates, Inc., 2021, pp.\u00a027263\u201327277. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/e4d2b6e6fdeca3e60e0f1a62fee3d9dd-Paper.pdf."},{"key":"10.3233\/AIC-230279_ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.540"},{"key":"10.3233\/AIC-230279_ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.58"},{"key":"10.3233\/AIC-230279_ref93","unstructured":"P.\u00a0Zhan, C.\u00a0Zheng, J.\u00a0Yang, Y.\u00a0Wang, L.\u00a0Wang, Y.\u00a0Wu and Y.\u00a0Zhang, PARSE: An efficient search method for black-box adversarial text attacks, in: Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12\u201317, 2022, N.\u00a0Calzolari, C.\u00a0Huang, H.\u00a0Kim, J.\u00a0Pustejovsky, L.\u00a0Wanner, K.\u00a0Choi, P.\u00a0Ryu, H.\u00a0Chen, L.\u00a0Donatelli, H.\u00a0Ji, S.\u00a0Kurohashi, P.\u00a0Paggio, N.\u00a0Xue, S.\u00a0Kim, Y.\u00a0Hahm, Z.\u00a0He, T.K.\u00a0Lee, E.\u00a0Santus, F.\u00a0Bond and S.\u00a0Na, eds, International Committee on Computational Linguistics, 2022, pp.\u00a04776\u20134787. https:\/\/aclanthology.org\/2022.coling-1.423."},{"key":"10.3233\/AIC-230279_ref94","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1559"},{"issue":"3","key":"10.3233\/AIC-230279_ref95","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3374217","article-title":"Adversarial attacks on deep-learning models in natural language processing","volume":"11","author":"Zhang","year":"2020","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"10.3233\/AIC-230279_ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.153"},{"key":"10.3233\/AIC-230279_ref97","unstructured":"T.\u00a0Zhang*, V.\u00a0Kishore*, F.\u00a0Wu*, K.Q.\u00a0Weinberger and Y.\u00a0Artzi, BERTScore: Evaluating text generation with BERT, in: International Conference on Learning Representations, 2020, https:\/\/openreview.net\/forum?id=SkeHuCVFDr."},{"key":"10.3233\/AIC-230279_ref98","unstructured":"Z.\u00a0Zhao, D.\u00a0Dua and S.\u00a0Singh, Generating natural adversarial examples, in: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings, OpenReview.net, 2018. https:\/\/openreview.net\/forum?id=H1BLjgZCb."},{"key":"10.3233\/AIC-230279_ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1328"},{"key":"10.3233\/AIC-230279_ref100","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2022.05.054","article-title":"Leveraging transferability and improved beam search in textual adversarial attacks","volume":"500","author":"Zhu","year":"2022","journal-title":"Neurocomputing"}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-230279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:41:51Z","timestamp":1741628511000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospress&doi=10.3233\/AIC-230279"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":94,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/aic-230279","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"value":"1875-8452","type":"electronic"},{"value":"0921-7126","type":"print"}],"subject":[],"published":{"date-parts":[[2024,9,18]]}}}