{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:50:49Z","timestamp":1776145849089,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government (MSIT) through the Artificial Intelligence Graduate School Program","award":["RS-2021-II211341"],"award-info":[{"award-number":["RS-2021-II211341"]}]},{"name":"Development of Artificial Intelligence Technology for Self-Improving Competency-Aware Learning Capabilities","award":["RS-2022-II220124"],"award-info":[{"award-number":["RS-2022-II220124"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3681579","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:01:14Z","timestamp":1775592074000},"page":"54148-54162","source":"Crossref","is-referenced-by-count":0,"title":["Single-Diffusion Representations for Out-of-Distribution Detection"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6870-2339","authenticated-orcid":false,"given":"Junhak","family":"Bae","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2365-0104","authenticated-orcid":false,"given":"Hyeokjun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8778-5573","authenticated-orcid":false,"given":"Youngjoon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref5","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-985x.2009.00624_10.x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.06.019"},{"key":"ref8","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ovadia"},{"key":"ref9","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref10","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016","journal-title":"arXiv:1610.02136"},{"key":"ref11","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref13","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref15","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref16","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref17","article-title":"Scaling out-of-distribution detection for real-world settings","author":"Hendrycks","year":"2019","journal-title":"arXiv:1911.11132"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00150"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02242"},{"key":"ref22","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","author":"Serr\u00e1","year":"2019","journal-title":"arXiv:1909.11480"},{"key":"ref23","article-title":"Multiscale score matching for out-of-distribution detection","author":"Mahmood","year":"2020","journal-title":"arXiv:2010.13132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00296"},{"key":"ref25","first-page":"22528","article-title":"Unsupervised out-of-distribution detection with diffusion inpainting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1395"},{"key":"ref27","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref28","article-title":"Do deep generative models know what they don\u2019t know?","author":"Nalisnick","year":"2018","journal-title":"arXiv:1810.09136"},{"key":"ref29","first-page":"20578","article-title":"Why normalizing flows fail to detect out-of-distribution data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kirichenko"},{"key":"ref30","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"ref32","first-page":"253","article-title":"Do text-free diffusion models learn discriminative visual representations?","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Mukhopadhyay"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"ref34","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv:2410.06940"},{"key":"ref35","article-title":"Mahalanobis++: Improving OOD detection via feature normalization","author":"Mueller","year":"2025","journal-title":"arXiv:2505.18032"},{"key":"ref36","article-title":"A geometry-based view of Mahalanobis OOD detection","author":"Janiak","year":"2025","journal-title":"arXiv:2510.15202"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0047-259X(03)00096-4"},{"key":"ref38","first-page":"606","article-title":"The effective rank: A measure of effective dimensionality","volume-title":"Proc. 15th Eur. Signal Process. Conf.","author":"Roy"},{"key":"ref39","article-title":"How to exploit hyperspherical embeddings for out-of-distribution detection?","author":"Ming","year":"2022","journal-title":"arXiv:2203. 04450"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00140"},{"key":"ref41","article-title":"A simple fix to Mahalanobis distance for improving near-OOD detection","author":"Ren","year":"2021","journal-title":"arXiv:2106.09022"},{"key":"ref42","article-title":"NODI: Out-of-distribution detection with noise from diffusion","author":"Zhou","year":"2024","journal-title":"arXiv:2401.08689"},{"key":"ref43","article-title":"Likelihood-based out-of-distribution detection with denoising diffusion probabilistic models","author":"Goodier","year":"2023","journal-title":"arXiv:2310.17432"},{"key":"ref44","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref46","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023","journal-title":"arXiv:2303.08797"},{"key":"ref47","article-title":"Probabilistic modeling of deep features for out-of-distribution and adversarial detection","author":"Ahuja","year":"2019","journal-title":"arXiv:1909.11786"},{"key":"ref48","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref50","article-title":"Representation entanglement for generation: Training diffusion transformers is much easier than you think","author":"Wu","year":"2025","journal-title":"arXiv:2507.01467"},{"key":"ref51","article-title":"SSD: A unified framework for self-supervised outlier detection","author":"Sehwag","year":"2021","journal-title":"arXiv:2103.12051"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718027"},{"key":"ref53","first-page":"115","article-title":"Applications of some measures of multivariate skewness and kurtosis in testing normality and robustness studies","author":"Mardia","year":"1974","journal-title":"Sankhy\u0101, Indian J. Statist., Ser. B"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2307\/2334770"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/cem.2680"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2307\/1403192"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1080\/03610929008830400"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2307\/2335012"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1990.10475751"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11475704.pdf?arnumber=11475704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:05:33Z","timestamp":1776143133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3681579","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}