{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:06:11Z","timestamp":1753880771258,"version":"3.41.2"},"reference-count":29,"publisher":"World Scientific Pub Co Pte Ltd","issue":"11","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61303190"],"award-info":[{"award-number":["61303190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2022,9,15]]},"abstract":"<jats:p> Adversarial attack is a serious threat to neural network-based natural language processing applications. Adversarial attack uses tiny well-crafted perturbations to mislead neural networks. While existing adversarial text attacks can achieve good attack effects, they still do not guarantee efficiency and robustness. The adversarial text attacks are more efficient if they use less perturbation to achieve a higher attack success rate. The attacks are more robust if they can achieve a higher success rate when defense strategies are applied. To improve the efficiency and robustness of the adversarial attack, we propose SMAL: Saliency Map Attack with Levenshtein-similarity. The proposed attack consists of two parts: (1) The saliency map measures the perturbation priority of each word. It considers not only the influence of each word on the classification result but also how to maintain the misled classification result to improve the robustness of the attack. (2) Levenshtein-similarity network embeds words into edit distance space. When perturbing sentences, some words are replaced by substitutions with less edit distance. This can reduce the amount of modification, which improves the efficiency of the attack. Since the words are embedded in edit distance space rather than semantic space, the semantic-based defense is not effective for this attack, which improves the robustness. The experiments show that SMAL achieves a higher attack success rate with fewer perturbations. Also, the proposed attack is better when attacking a classifier defended by adversarial training. <\/jats:p>","DOI":"10.1142\/s021800142253007x","type":"journal-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T07:51:53Z","timestamp":1654761113000},"source":"Crossref","is-referenced-by-count":2,"title":["Towards an Efficient and Robust Adversarial Attack Against Neural Text Classifier"],"prefix":"10.1142","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2847-928X","authenticated-orcid":false,"given":"Zibo","family":"Yi","sequence":"first","affiliation":[{"name":"Information Research Center of Military Science, PLA Academy of Military Science, No. 26, Fucheng Road, Haidian District, Beijing 100142, P.\u00a0R.\u00a0China"}]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, No. 109, Deya Road, Kaifu District, Changsha, Hunan 410073, P.\u00a0R.\u00a0China"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, No. 109, Deya Road, Kaifu District, Changsha, Hunan 410073, P.\u00a0R.\u00a0China"}]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, No. 109, Deya Road, Kaifu District, Changsha, Hunan 410073, P.\u00a0R.\u00a0China"}]},{"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, No. 109, Deya Road, Kaifu District, Changsha, Hunan 410073, P.\u00a0R.\u00a0China"}]},{"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, No. 109, Deya Road, Kaifu District, Changsha, Hunan 410073, P.\u00a0R.\u00a0China"}]}],"member":"219","published-online":{"date-parts":[[2022,8,31]]},"reference":[{"key":"S021800142253007XBIB002","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1316"},{"volume-title":"ICLR 2015: Int. Conf. Learning Representations 2015","year":"2015","author":"Bahdanau D.","key":"S021800142253007XBIB003"},{"volume-title":"6th International Conference on Learning Representations, (ICLR) 2018","year":"2018","author":"Belinkov Y.","key":"S021800142253007XBIB004"},{"key":"S021800142253007XBIB005","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"S021800142253007XBIB006","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2877359"},{"key":"S021800142253007XBIB007","first-page":"1","author":"Chen J.","year":"2020","journal-title":"IEEE Trans. Ind. Inf."},{"key":"S021800142253007XBIB008","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2006"},{"key":"S021800142253007XBIB009","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00016"},{"key":"S021800142253007XBIB011","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"S021800142253007XBIB012","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"S021800142253007XBIB013","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"S021800142253007XBIB015","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1170"},{"key":"S021800142253007XBIB016","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"S021800142253007XBIB017","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"S021800142253007XBIB018","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"volume-title":"3rd International Conference on Learning Representations (ICLR)","year":"2015","author":"Kingma D. P.","key":"S021800142253007XBIB019"},{"volume-title":"6th International Conference on Learning Representations (ICLR)","year":"2018","author":"Kuleshov V.","key":"S021800142253007XBIB020"},{"key":"S021800142253007XBIB023","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"S021800142253007XBIB024","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23138"},{"key":"S021800142253007XBIB025","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/585"},{"key":"S021800142253007XBIB026","first-page":"142","volume-title":"Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Maas A. L.","year":"2011"},{"volume-title":"5th International Conference on Learning Representations (ICLR)","year":"2017","author":"Miyato T.","key":"S021800142253007XBIB027"},{"key":"S021800142253007XBIB028","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"S021800142253007XBIB029","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"S021800142253007XBIB030","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2016.7795300"},{"key":"S021800142253007XBIB031","first-page":"311","volume-title":"Proc. 40th Annual Meeting on Association for Computational Linguistics","author":"Papineni K.","year":"2002"},{"key":"S021800142253007XBIB032","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"S021800142253007XBIB034","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_71"},{"key":"S021800142253007XBIB037","first-page":"2335","volume-title":"Proc. COLING 2014, 25th Int. Conf. Computational Linguistics: Technical Papers","author":"Zeng D.","year":"2014"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S021800142253007X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T07:50:21Z","timestamp":1663141821000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S021800142253007X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,31]]},"references-count":29,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,9,15]]}},"alternative-id":["10.1142\/S021800142253007X"],"URL":"https:\/\/doi.org\/10.1142\/s021800142253007x","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2022,8,31]]},"article-number":"2253007"}}