{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T03:31:33Z","timestamp":1784172693090,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902082"],"award-info":[{"award-number":["61902082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1636215"],"award-info":[{"award-number":["U1636215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1706003"],"award-info":[{"award-number":["2019YFB1706003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Key R&D Program of China","award":["2019B010136003"],"award-info":[{"award-number":["2019B010136003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tnse.2020.2996738","type":"journal-article","created":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T20:51:48Z","timestamp":1590180708000},"page":"921-932","source":"Crossref","is-referenced-by-count":91,"title":["Gradient Shielding: Towards Understanding Vulnerability of Deep Neural Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7546-852X","authenticated-orcid":false,"given":"Zhaoquan","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5474-991X","authenticated-orcid":false,"given":"Weixiong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-8274","authenticated-orcid":false,"given":"Chuanjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4120-7716","authenticated-orcid":false,"given":"Hui","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3610-9185","authenticated-orcid":false,"given":"Le","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.80026"},{"key":"ref33","article-title":"Simple black-box adversarial perturbations for deep networks","author":"narodytska","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref30","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref36","article-title":"Transferability in machine learning: From phenomena to black-box attacks using adversarial samples","author":"papernot","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.153"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref61","article-title":"Mitigating adversarial effects through randomization","author":"xie","year":"2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054358"},{"key":"ref28","article-title":"Adversarial machine learning at scale","author":"kurakin","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref27","article-title":"AdvHat: Real-world adversarial attack on ArcFace Face ID system","author":"komkov","year":"2019"},{"key":"ref65","article-title":"Generating natural adversarial examples","author":"zhao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9053896","article-title":"Transformer transducer: A streamable speech recognition model with transformer encoders and RNN-T loss","author":"zhang","year":"2020"},{"key":"ref29","article-title":"Adversarial examples in the physical world","author":"kurakin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","article-title":"Synthesizing robust adversarial examples","author":"athalye","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref20","article-title":"Learning with a strong adversary","author":"huang","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1062"},{"key":"ref21","article-title":"Fortified networks: Improving the robustness of deep networks by modeling the manifold of hidden representations","author":"lamb","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00783"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00111"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301962"},{"key":"ref25","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref51","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2687918"},{"key":"ref58","article-title":"Ensemble adversarial training: Attacks and defenses","author":"tramer","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","article-title":"The space of transferable adversarial examples","author":"tramer","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2951620"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2938778"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2907754"},{"key":"ref53","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"0","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2008.319"},{"key":"ref11","article-title":"Robust physical-world attacks on deep learning","author":"eykholt","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref40","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref12","article-title":"Physical adversarial examples for object detectors","author":"eykholt","year":"2018"},{"key":"ref13","article-title":"Adversarial vulnerability for anyclassifier","author":"fawzi","year":"2018"},{"key":"ref14","article-title":"The relationship between high-dimensional geometry and adversarial examples","author":"gilmer","year":"2018"},{"key":"ref15","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","article-title":"Towards deep neural network architectures robust to adversarial examples","author":"gu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971004"},{"key":"ref18","article-title":"Countering adversarial images using input transformations","author":"guo","year":"2018","journal-title":"Int Conf Learn Representations"},{"key":"ref19","article-title":"Deep residual learning for image recognition","author":"he","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref3","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","author":"athalye","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","article-title":"ArcFace: Additive angular margin loss for deep face recognition","author":"deng","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref8","article-title":"CAAD 2018: Powerful none-access black-box attack based on adversarial transformation network","author":"dong","year":"2018"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref49","article-title":"MASS: Masked sequence to sequence pre-training","author":"song","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref46","article-title":"A simple explanation for the existence of adversarial examples with small hamming distance","author":"shamir","year":"0"},{"key":"ref45","article-title":"Defending against adversarial images using basis functions transformations","author":"shaham","year":"2018"},{"key":"ref48","article-title":"Adversarial generative nets: Neural network attacks on state-of-the-art face recognition","author":"sharif","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978392"},{"key":"ref42","article-title":"Adversarial manipulation of deep representations","author":"sabour","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.58"},{"key":"ref44","article-title":"Are adversarial examples inevitable?","author":"shafahi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","article-title":"UPSET and ANGRI: Breaking high performance image classifiers","author":"sarkar","year":"2017"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488902\/9475902\/09099073.pdf?arnumber=9099073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T17:17:08Z","timestamp":1666631828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9099073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":66,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnse.2020.2996738","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}