{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T10:04:40Z","timestamp":1766311480643,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3432773","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T19:50:58Z","timestamp":1721764258000},"page":"138341-138350","source":"Crossref","is-referenced-by-count":3,"title":["Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1039-4854","authenticated-orcid":false,"given":"Hanen","family":"Issaoui","sequence":"first","affiliation":[{"name":"Research Team in Intelligent Machines (RTIM), University of Gabes, Gabes, Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asma","family":"Eladel","sequence":"additional","affiliation":[{"name":"Research Team in Intelligent Machines (RTIM), University of Gabes, Gabes, Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1844-975X","authenticated-orcid":false,"given":"Ahmed","family":"Zouinkhi","sequence":"additional","affiliation":[{"name":"MACS Laboratory LR 16ES22, National Engineering School of Gabes, University of Gabes, Gabes, Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1466-9957","authenticated-orcid":false,"given":"Mourad","family":"Zaied","sequence":"additional","affiliation":[{"name":"Research Team in Intelligent Machines (RTIM), University of Gabes, Gabes, Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1434-5689","authenticated-orcid":false,"given":"Lazhar","family":"Khriji","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering, Sultan Qaboos University, Muscat, Oman"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9651-9282","authenticated-orcid":false,"given":"Sarvar Hussain","family":"Nengroo","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.30.5.050901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_8"},{"key":"ref3","first-page":"201","article-title":"CryptoNets: Applying neural networks to encrypted\n                        data with high throughput and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilad-Bachrach"},{"key":"ref4","first-page":"35","article-title":"Privacy-preserving classification on deep neural\n                        network","volume":"2017","author":"Chabanne","year":"2017","journal-title":"IACR Cryptol. ePrint\n                    Arch."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46805-6_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1117\/12.2679393"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/spw54247.2022.9833884"},{"key":"ref8","first-page":"3320","article-title":"How transferable are features in deep neural\n                        networks","volume-title":"Proc. Neural Inf. Process.\n                        Syst.","author":"Yosinski"},{"key":"ref9","article-title":"Explaining and harnessing adversarial\n                        examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_32"},{"key":"ref11","article-title":"Batch normalization: Accelerating deep network\n                        training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref12","article-title":"Towards deep learning models resistant to adversarial\n                        attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref13","article-title":"Certified adversarial robustness via randomized\n                        smoothing","author":"Cohen","year":"2019","journal-title":"arXiv:1902.02918"},{"key":"ref14","first-page":"1","article-title":"Stochastic security: Adversarial defense using\n                        long-run dynamics of energy-based models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hill"},{"key":"ref15","article-title":"Crypto-nets: Neural networks over encrypted\n                        data","author":"Xie","year":"2014","journal-title":"arXiv:1412.6181"},{"key":"ref16","first-page":"1","article-title":"Attacks which do not kill training make adversarial\n                        learning stronger","volume-title":"Proc. Int. Conf. Mach.\n                        Learn. (ICML)","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/el:19891114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00040"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC55077.2022.9886997"},{"key":"ref21","first-page":"1","article-title":"Intriguing properties of neural\n                        networks","volume":"1","author":"Szegedy","year":"2014","journal-title":"Comput. Vis. Pattern\n                        Recognit."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978392"},{"key":"ref24","first-page":"1","article-title":"Universal adversarial perturbations against semantic\n                        image segmentation","volume":"1","author":"Seyed","year":"2017","journal-title":"Comput. Vis. Pattern\n                        Recognit."},{"key":"ref25","article-title":"Ensemble adversarial training: Attacks and\n                        defenses","author":"Tram\u00e8r","year":"2017","journal-title":"arXiv:1705.07204"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14311\/NNW.2012.22.023"},{"key":"ref27","article-title":"CryptoDL: Deep neural networks over encrypted\n                        data","author":"Hesamifard","year":"2017","journal-title":"arXiv:1711.05189"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"ref29","first-page":"1","article-title":"Everything you should know about dropouts and batch\n                        normalization in CNN","volume":"1","author":"Dwivedi","year":"2022","journal-title":"Developers Corner,\n                        Anal. India Mag."},{"key":"ref30","article-title":"Learning activation functions to improve deep neural\n                        networks","author":"Agostinelli","year":"2014","journal-title":"arXiv:1412.6830"},{"key":"ref31","first-page":"1","article-title":"Towards deep neural network architectures robust to\n                        adversarial examples","volume-title":"Proc. Int. Conf.\n                        Learn. Represent.","author":"Gu"},{"key":"ref32","article-title":"Visual causal feature\n                    learning","author":"Chalupka","year":"2014","journal-title":"arXiv:1412.2309"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICISFall51598.2021.9627468"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys57074.2022.00255"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn52387.2021.9533495"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3118977"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icece48499.2019.9058535"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12028"},{"key":"ref39","article-title":"Adversarial attack attribution: Discovering\n                        attributable signals in adversarial ML attacks","author":"Dotter","year":"2021","journal-title":"arXiv:2101.02899"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10606465.pdf?arnumber=10606465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:58:39Z","timestamp":1732665519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10606465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3432773","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}