{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:25:29Z","timestamp":1778347529972,"version":"3.51.4"},"reference-count":181,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Deputyship for Research and Innovation, Ministry of Education, Saudi Arabia","award":["1120"],"award-info":[{"award-number":["1120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3146405","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T21:48:02Z","timestamp":1643320082000},"page":"17043-17077","source":"Crossref","is-referenced-by-count":34,"title":["Adversarial Machine Learning in Text Processing: A Literature Survey"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7832-5081","authenticated-orcid":false,"given":"Izzat","family":"Alsmadi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8049-1425","authenticated-orcid":false,"given":"Nura","family":"Aljaafari","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3375-0310","authenticated-orcid":false,"given":"Mahmoud","family":"Nazzal","sequence":"additional","affiliation":[]},{"given":"Shadan","family":"Alhamed","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7040-8963","authenticated-orcid":false,"given":"Ahmad H.","family":"Sawalmeh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3990-9038","authenticated-orcid":false,"given":"Conrado P.","family":"Vizcarra","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1583-713X","authenticated-orcid":false,"given":"Abdallah","family":"Khreishah","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9479-4985","authenticated-orcid":false,"given":"Muhammad","family":"Anan","sequence":"additional","affiliation":[]},{"given":"Abdulelah","family":"Algosaibi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5682-6237","authenticated-orcid":false,"given":"Mohammed Abdulaziz","family":"Al-Naeem","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1903-0480","authenticated-orcid":false,"given":"Adel","family":"Aldalbahi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7778-2838","authenticated-orcid":false,"given":"Abdulaziz","family":"Al-Humam","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_40"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5188-5"},{"key":"ref3","article-title":"Explaining and harnessing adversarial examples","volume-title":"arXiv:1412.6572","author":"Goodfellow","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133990"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W18-2503","article-title":"Texar: A modularized, versatile, and extensible toolkit for text generation","volume-title":"arXiv:1809.00794","author":"Hu","year":"2018"},{"key":"ref7","first-page":"1","article-title":"RelGAN: Relational generative adversarial networks for text generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3526"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11957"},{"key":"ref12","article-title":"Adversarial ranking for language generation","volume-title":"arXiv:1705.11001","author":"Lin","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref14","first-page":"4601","article-title":"Professor forcing: A new algorithm for training recurrent networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lamb"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6490"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0017"},{"key":"ref17","first-page":"246","article-title":"Hierarchical probabilistic neural network language model","volume-title":"Proc. AISTATS","volume":"5","author":"Morin"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","article-title":"Sequence level training with recurrent neural networks","volume-title":"arXiv:1511.06732","author":"Ranzato","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/048615a0"},{"key":"ref23","article-title":"Learning implicit generative models with the method of learned moments","volume-title":"arXiv:1806.11006","author":"Ravuri","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/1912775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref26","article-title":"Improved techniques for training GANs","volume-title":"arXiv:1606.03498","author":"Salimans","year":"2016"},{"key":"ref27","first-page":"2513","article-title":"Fisher GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mroueh"},{"key":"ref28","article-title":"Adversarial generalized method of moments","volume-title":"arXiv:1803.07164","author":"Lewis","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkad025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(88)90031-5"},{"key":"ref33","article-title":"Auto-encoding variational Bayes","volume-title":"arXiv:1312.6114","author":"Kingma","year":"2013"},{"key":"ref34","article-title":"Mitigating adversarial effects through randomization","volume-title":"arXiv:1711.01991","author":"Xie","year":"2017"},{"key":"ref35","first-page":"4666","article-title":"Adversarial text generation via feature-mover\u2019s distance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref36","article-title":"SDA: Improving text generation with self data augmentation","volume-title":"arXiv:2101.03236","author":"Yu","year":"2021"},{"key":"ref37","article-title":"Towards uncertainty and efficiency in reinforcement learning","author":"Zhang","year":"2021"},{"key":"ref38","article-title":"Learning natural language generation from scratch","volume-title":"arXiv:2109.09371","author":"Donati","year":"2021"},{"key":"ref39","article-title":"Adversarial generation of natural language","volume-title":"arXiv:1705.10929","author":"Rajeswar","year":"2017"},{"key":"ref40","article-title":"Maximum-likelihood augmented discrete generative adversarial networks","volume-title":"arXiv:1702.07983","author":"Che","year":"2017"},{"key":"ref41","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref42","article-title":"Generating text with deep reinforcement learning","volume-title":"arXiv:1510.09202","author":"Guo","year":"2015"},{"key":"ref43","article-title":"An actor-critic algorithm for sequence prediction","volume-title":"arXiv:1607.07086","author":"Bahdanau","year":"2016"},{"key":"ref44","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"arXiv:1611.00712","author":"Maddison","year":"2016"},{"key":"ref45","first-page":"4006","article-title":"Adversarial feature matching for text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref46","article-title":"GANS for sequences of discrete elements with the Gumbel-softmax distribution","volume-title":"arXiv:1611.04051","author":"Kusner","year":"2016"},{"key":"ref47","article-title":"Learning deep models via optimal transport distance","author":"Chen","year":"2021"},{"key":"ref48","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"arXiv:1611.01144","author":"Jang","year":"2016"},{"key":"ref49","first-page":"227","article-title":"You only propagate once: Accelerating adversarial training via maximal principle","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref50","article-title":"Improving Sequence-to-Sequence learning via optimal transport","volume-title":"arXiv:1901.06283","author":"Chen","year":"2019"},{"key":"ref51","article-title":"FeUdal networks for hierarchical reinforcement learning","volume-title":"arXiv:1703.01161","author":"Vezhnevets","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2896437"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108098"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05960-5"},{"key":"ref56","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Bengio"},{"key":"ref57","article-title":"A neural conversational model","volume-title":"arXiv:1506.05869","author":"Vinyals","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1239"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1081"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016908"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.03.050"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00609"},{"key":"ref64","article-title":"Toward controlled generation of text","volume-title":"arXiv:1703.00955","author":"Hu","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.577"},{"key":"ref66","first-page":"1","article-title":"TopicGAN: Unsupervised text generation from explainable latent topics","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref67","article-title":"An unsupervised joint system for text generation from knowledge graphs and semantic parsing","volume-title":"arXiv:1904.09447","author":"Schmitt","year":"2019"},{"key":"ref68","volume-title":"Going GREAN: A Novel Framework and Evaluation Metric for the Graph-to-Text Generation Task","author":"Sheffer","year":"2020"},{"key":"ref69","article-title":"Text generation from knowledge graphs with graph transformers","volume-title":"arXiv:1904.02342","author":"Koncel-Kedziorski","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.217"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1032"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2018.00046"},{"key":"ref73","article-title":"Neural text generation: Past, present and beyond","volume-title":"arXiv:1803.07133","author":"Lu","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00673"},{"key":"ref75","article-title":"LSTM vs. GRU vs. bidirectional RNN for script generation","volume-title":"arXiv:1908.04332","author":"Mangal","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3415088.3415114"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4009"},{"key":"ref78","article-title":"What to talk about and how? Selective generation using LSTMs with coarse-to-fine alignment","volume-title":"arXiv:1509.00838","author":"Mei","year":"2015"},{"key":"ref79","article-title":"MaskGAN: Better text generation via filling in the_","volume-title":"arXiv:1801.07736","author":"Fedus","year":"2018"},{"key":"ref80","first-page":"1","article-title":"Generating text with recurrent neural networks","volume-title":"Proc. ICML","author":"Sutskever"},{"key":"ref81","article-title":"NLG vs. templates","volume-title":"arXiv:cmp-lg\/9504013","author":"Reiter","year":"1995"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1162\/0891201053630291"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1356"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1263"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16952-6_32"},{"key":"ref86","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"27","author":"Sutskever"},{"key":"ref87","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"arXiv:1409.0473","author":"Bahdanau","year":"2014"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1144"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3512467"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/355598.362773"},{"key":"ref91","first-page":"1","article-title":"An efficient recursive transition network parser for Arabic language","volume-title":"Proc. World Congr. Eng.","volume":"2","author":"Bataineh"},{"key":"ref92","article-title":"On the simulation of postmodernism and mental debility using recursive transition networks","author":"Bulhak","year":"1996"},{"key":"ref93","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref94","first-page":"7299","article-title":"Relational recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro"},{"key":"ref95","article-title":"Exploring the limits of language modeling","volume-title":"arXiv:1602.02410","author":"Jozefowicz","year":"2016"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-564"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00115"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1409"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2049"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6443"},{"key":"ref101","article-title":"Evaluating text GANs as language models","volume-title":"arXiv:1810.12686","author":"Tevet","year":"2018"},{"key":"ref102","article-title":"Intriguing properties of neural networks","volume-title":"arXiv:1312.6199","author":"Szegedy","year":"2013"},{"key":"ref103","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"arXiv:1706.06083","author":"Madry","year":"2017"},{"key":"ref104","first-page":"1","article-title":"Thermometer encoding: One hot way to resist adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Buckman"},{"key":"ref105","article-title":"Defensive quantization: When efficiency meets robustness","volume-title":"arXiv:1904.08444","author":"Lin","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref108","article-title":"Adversarial attacks and defences: A survey","volume-title":"arXiv:1810.00069","author":"Chakraborty","year":"2018"},{"key":"ref109","article-title":"Adversarial machine learning at scale","volume-title":"arXiv:1611.01236","author":"Kurakin","year":"2016"},{"key":"ref110","article-title":"ME-Net: Towards effective adversarial robustness with matrix estimation","volume-title":"arXiv:1905.11971","author":"Yang","year":"2019"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref113","article-title":"Stochastic activation pruning for robust adversarial defense","volume-title":"arXiv:1803.01442","author":"Dhillon","year":"2018"},{"key":"ref114","article-title":"Adversarial logit pairing","volume-title":"arXiv:1803.06373","author":"Kannan","year":"2018"},{"key":"ref115","article-title":"L\u2082-nonexpansive neural networks","volume-title":"arXiv:1802.07896","author":"Qian","year":"2018"},{"key":"ref116","article-title":"Robust learning with Jacobian regularization","volume-title":"arXiv:1908.02729","author":"Hoffman","year":"2019"},{"key":"ref117","article-title":"The robust manifold defense: Adversarial training using generative models","volume-title":"arXiv:1712.09196","author":"Jalal","year":"2017"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933524"},{"key":"ref120","article-title":"Efficient two-step adversarial defense for deep neural networks","volume-title":"arXiv:1810.03739","author":"Chang","year":"2018"},{"key":"ref121","article-title":"Fast is better than free: Revisiting adversarial training","volume-title":"arXiv:2001.03994","author":"Wong","year":"2020"},{"key":"ref122","first-page":"3358","article-title":"Adversarial training for free!","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref123","article-title":"Adversarially robust generalization requires more data","volume-title":"arXiv:1804.11285","author":"Schmidt","year":"2018"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref125","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref126","article-title":"Network in network","volume-title":"arXiv:1312.4400","author":"Lin","year":"2013"},{"key":"ref127","article-title":"Logit pairing methods can fool gradient-based attacks","volume-title":"arXiv:1810.12042","author":"Mosbach","year":"2018"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref129","first-page":"163","article-title":"Optimization and global minimization methods suitable for neural networks","volume":"2","author":"Duch","year":"1998","journal-title":"Neural Comput. Surveys"},{"key":"ref130","article-title":"Understanding neural networks through representation erasure","volume-title":"arXiv:1612.08220","author":"Li","year":"2016"},{"key":"ref131","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"arXiv:1510.00149","author":"Han","year":"2015"},{"key":"ref132","article-title":"Trained ternary quantization","volume-title":"arXiv:1612.01064","author":"Zhu","year":"2016"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11663"},{"key":"ref135","article-title":"Towards efficient training for neural network quantization","volume-title":"arXiv:1912.10207","author":"Jin","year":"2019"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"ref137","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","volume":"37","author":"Kusner"},{"key":"ref138","article-title":"Correspondence between perplexity scores and human evaluation of generated TV-show scripts","author":"Keukeleire","year":"2020"},{"key":"ref139","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref140","article-title":"A diversity-promoting objective function for neural conversation models","volume-title":"arXiv:1510.03055","author":"Li","year":"2015"},{"key":"ref141","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization AC","author":"Lin"},{"key":"ref142","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref143","article-title":"Real-valued (medical) time series generation with recurrent conditional GANs","volume-title":"arXiv:1706.02633","author":"Esteban","year":"2017"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2915544"},{"key":"ref145","article-title":"Eval all, trust a few, do wrong to none: Comparing sentence generation models","volume-title":"arXiv:1804.07972","author":"C\u00edfka","year":"2018"},{"key":"ref146","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume-title":"arXiv:1504.00325","author":"Chen","year":"2015"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.3390\/app9102024"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/595"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1074"},{"key":"ref150","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8030292"},{"key":"ref153","article-title":"Understanding LSTM networks","author":"Olah","year":"2015"},{"key":"ref154","first-page":"1","article-title":"Recent trends in deep learning based natural language processing","volume":"abs\/1708.02709","author":"Young","year":"2017","journal-title":"CoRR"},{"key":"ref155","article-title":"GraphPB: Graphical representations of prosody boundary in speech synthesis","volume-title":"arXiv:2012.02626","author":"Sun","year":"2020"},{"key":"ref156","volume-title":"Understanding LSTM Networks","year":"2015"},{"key":"ref157","first-page":"1","article-title":"Comparative study of CNN and RNN for natural language processing","volume":"abs\/1702.01923","author":"Yin","year":"2017","journal-title":"CoRR"},{"key":"ref158","first-page":"1","article-title":"An end to end model for automatic music generation: Combining deep raw and symbolic audio networks","volume-title":"Proc. Musical Metacreation Workshop 9th Int. Conf. Comput. Creativity","author":"Manzelli"},{"key":"ref159","article-title":"Defense against adversarial attacks in NLP via Dirichlet neighborhood ensemble","volume-title":"arXiv:2006.11627","author":"Zhou","year":"2020"},{"key":"ref160","article-title":"Adversarial training methods for semi-supervised text classification","volume-title":"arXiv:1605.07725","author":"Miyato","year":"2016"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/601"},{"key":"ref162","article-title":"FreeLB: Enhanced adversarial training for natural language understanding","volume-title":"arXiv:1909.11764","author":"Zhu","year":"2019"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1419"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref166","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"arXiv:1902.02918","author":"Cohen","year":"2019"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_23"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1496"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1316"},{"key":"ref170","article-title":"Deep text classification can be fooled","volume-title":"arXiv:1704.08006","author":"Liang","year":"2017"},{"key":"ref171","article-title":"DANCin SEQ2SEQ: Fooling text classifiers with adversarial text example generation","volume-title":"arXiv:1712.05419","author":"Wong","year":"2017"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5767"},{"key":"ref173","article-title":"On adversarial examples for character-level neural machine translation","volume-title":"arXiv:1806.09030","author":"Ebrahimi","year":"2018"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1425"},{"key":"ref175","article-title":"Understanding and diagnosing vulnerability under adversarial attacks","volume-title":"arXiv:2007.08716","author":"Zheng","year":"2020"},{"key":"ref176","article-title":"HotFlip: White-box adversarial examples for text classification","volume-title":"arXiv:1712.06751","author":"Ebrahimi","year":"2017"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102303"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.012"},{"issue":"101","key":"ref179","first-page":"102","article-title":"DAWNBench: An end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman","year":"2017","journal-title":"Training"},{"key":"ref180","article-title":"Mixed precision training","volume-title":"arXiv:1710.03740","author":"Micikevicius","year":"2017"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09693527.pdf?arnumber=9693527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:50:54Z","timestamp":1705186254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":181,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3146405","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}