{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T17:47:52Z","timestamp":1743788872303,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Franklin Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3263210","type":"journal-article","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T19:21:22Z","timestamp":1680117682000},"page":"32716-32732","source":"Crossref","is-referenced-by-count":7,"title":["Probing the Purview of Neural Networks via Gradient Analysis"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8749-7651","authenticated-orcid":false,"given":"Jinsol","family":"Lee","sequence":"first","affiliation":[{"name":"Omni Lab for Intelligent Visual Engineering and Science (OLIVES), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charlie","family":"Lehman","sequence":"additional","affiliation":[{"name":"Omni Lab for Intelligent Visual Engineering and Science (OLIVES), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8743-7058","authenticated-orcid":false,"given":"Mohit","family":"Prabhushankar","sequence":"additional","affiliation":[{"name":"Omni Lab for Intelligent Visual Engineering and Science (OLIVES), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6818-8001","authenticated-orcid":false,"given":"Ghassan","family":"AlRegib","sequence":"additional","affiliation":[{"name":"Omni Lab for Intelligent Visual Engineering and Science (OLIVES), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00028"},{"key":"ref2","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803317"},{"key":"ref4","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goodfellow"},{"key":"ref5","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Guo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190679"},{"key":"ref7","first-page":"1","article-title":"Gradient-based adversarial and out-of-distribution detection","volume-title":"Proc. ICML Workshop New Frontiers Adversarial Mach. Learn.","author":"Lee"},{"key":"ref8","first-page":"1","article-title":"CURE-TSR: Challenging unreal and real environments for traffic sign recognition","volume-title":"Proc. NeurIPS Workshop Mach. Learn. Intell. Transp. Syst.","author":"Temel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI52829.2022.9761432"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref11","article-title":"Big neural networks waste capacity","author":"Dauphin","year":"2013","journal-title":"arXiv:1301.3583"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/1116025"},{"key":"ref14","first-page":"1","article-title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR) Workshop","author":"Neyshabur"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref17","first-page":"1","article-title":"On the number of linear regions of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Montufar"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00575"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00308"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20092"},{"key":"ref24","first-page":"1","article-title":"Adversarially robust generalization requires more data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Schmidt"},{"key":"ref25","first-page":"1","article-title":"Measuring the intrinsic dimension of objective landscapes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref26","first-page":"1","article-title":"Intrinsic dimension of data representations in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ansuini"},{"key":"ref27","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref28","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref29","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref30","article-title":"Learning confidence for out-of-distribution detection in neural networks","author":"DeVries","year":"2018","journal-title":"arXiv:1802.04865"},{"key":"ref31","first-page":"1","article-title":"Characterizing adversarial subspaces using local intrinsic dimensionality","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref32","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":"ref33","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2022.3163871"},{"key":"ref40","first-page":"1","article-title":"Introspective learning: A two-stage approach for inference in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Prabhushankar"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99978-4_9"},{"key":"ref43","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506393"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref48"},{"key":"ref49","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","first-page":"11839","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tack"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-136"},{"key":"ref55","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":"ref56","first-page":"1","article-title":"A new defense against adversarial images: Turning a weakness into a strength","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24775-3_3"},{"key":"ref58","first-page":"1","article-title":"Inference for the generalization error","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Nadeau"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2601119"},{"key":"ref60","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Coates"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10087225.pdf?arnumber=10087225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T09:39:58Z","timestamp":1709458798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10087225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3263210","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}