{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:40:46Z","timestamp":1780501246052,"version":"3.54.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3623900","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:57:35Z","timestamp":1760983055000},"page":"186138-186167","source":"Crossref","is-referenced-by-count":1,"title":["On the Adversarial Robustness of Hand-Crafted Features and Their Role in Defending Adversarial Examples"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4689-6618","authenticated-orcid":false,"given":"Shuohan","family":"Xue","sequence":"first","affiliation":[{"name":"1School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0781-6124","authenticated-orcid":false,"given":"Lihui","family":"Wu","sequence":"additional","affiliation":[{"name":"1School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2799-7395","authenticated-orcid":false,"given":"Charith","family":"Abhayaratne","sequence":"additional","affiliation":[{"name":"1School of Electrical and Electronic Engineering, The University of Sheffield, Sheffield, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3004171"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref5","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Szegedy"},{"key":"ref6","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015","journal-title":"arXiv:1412.6572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref10","article-title":"Feature squeezing: Detecting adversarial examples in deep neural networks","author":"Xu","year":"2017","journal-title":"arXiv:1704.01155"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2018.2874243"},{"key":"ref12","first-page":"1","article-title":"Countering adversarial images using input transformations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Guo"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3689091.3690090"},{"key":"ref14","first-page":"535","article-title":"Generative adversarial detection","volume-title":"Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV)","author":"Li"},{"key":"ref15","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref16","article-title":"On detecting adversarial perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Metzen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref18","article-title":"SOAR: Second-order adversarial regularization","author":"Ma","year":"2020","journal-title":"arXiv:2004.01832"},{"key":"ref19","first-page":"419","article-title":"Deep defense: Training DNNs with improved adversarial robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Yan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21413"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2326991"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2175739"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545438"},{"issue":"6","key":"ref31","first-page":"1100","article-title":"Image matching from handcrafted to deep features: A survey","volume":"127","author":"Zhang","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298904"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2855738"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref36","article-title":"Robustness may be at odds with accuracy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tsipras"},{"key":"ref37","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref38","first-page":"10882","article-title":"On the convergence and robustness of adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref39","article-title":"Bag of tricks for adversarial training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Pang"},{"key":"ref40","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce"},{"key":"ref41","article-title":"A study of the effect of JPG compression on adversarial images","author":"Karolina Dziugaite","year":"2016","journal-title":"arXiv:1608.00853"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00095"},{"key":"ref43","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Athalye"},{"key":"ref44","article-title":"PixelDefend: Leveraging generative models to understand and defend against adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref46","article-title":"Robust learning with Jacobian regularization","author":"Hoffman","year":"2019","journal-title":"arXiv:1908.02729"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_32"},{"key":"ref48","article-title":"On the (statistical) detection of adversarial examples","author":"Grosse","year":"2017","journal-title":"arXiv:1702.06280"},{"key":"ref49","first-page":"1152","article-title":"Detecting adversarial samples from artifacts in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Feinman"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.615"},{"key":"ref51","first-page":"21692","article-title":"Detecting adversarial examples is (nearly) as hard as classifying them","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Tram\u00e8r"},{"key":"ref52","first-page":"1","article-title":"Characterizing adversarial subspaces using local intrinsic dimensionality","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01479"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref55","first-page":"44","article-title":"Are accuracy and robustness at odds? The case of sift features","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Rozsa"},{"key":"ref56","article-title":"Foveation-based mechanisms alleviate adversarial examples","author":"Luo","year":"2015","journal-title":"arXiv:1511.06292"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20169"},{"key":"ref62","article-title":"Fast is better than free: Revisiting adversarial training","author":"Wong","year":"2020","journal-title":"arXiv:2001.03994"},{"key":"ref63","article-title":"Adaptive adversarial training to improve adversarial robustness of DNNs for medical image segmentation and detection","author":"Ma","year":"2022","journal-title":"arXiv:2206.01736"},{"key":"ref64","first-page":"15084","article-title":"Practical evaluation of adversarial robustness via adaptive auto attack","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ye"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00427"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref69","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1190\/1.1441328"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref73","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wong"},{"key":"ref74","first-page":"5014","article-title":"Adversarially robust generalization requires more data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schmidt"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11208633.pdf?arnumber=11208633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:20Z","timestamp":1762368080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3623900","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}