{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:56:28Z","timestamp":1774594588264,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/ieeeconf67917.2025.11443828","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:47:37Z","timestamp":1774554457000},"page":"227-231","source":"Crossref","is-referenced-by-count":0,"title":["Out-of-Distribution Detection via Uncertainty Quantification in Diffusion Models"],"prefix":"10.1109","author":[{"given":"Shirin","family":"Shoushtari","sequence":"first","affiliation":[{"name":"WashU,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"WashU,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulugbek S.","family":"Kamilov","sequence":"additional","affiliation":[{"name":"UW-Madison,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref2","article-title":"\u201cWhy Did the Model Fail?\u201d: Attributing Model Performance Changes to Distribution Shifts","volume-title":"Proc. ICML","volume":"abs\/2210.10769","author":"Zhang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00296"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1395"},{"key":"ref5","article-title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","volume-title":"Proc. ICLR","author":"Salimans"},{"key":"ref6","article-title":"Glow: Generative Flow with Invertible 1x1 Convolutions","volume-title":"Proc. NeurIPS","volume":"31","author":"Kingma"},{"key":"ref7","first-page":"3232","article-title":"Density of States Estimation for Out of Distribution Detection","volume-title":"Proc. AISTATS","author":"Morningstar"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-95918-9_12"},{"key":"ref9","article-title":"WAIC, but Why? Generative Ensembles for Robust Anomaly Detection","author":"Choi","year":"2018"},{"key":"ref10","article-title":"Do Deep Generative Models Know What They Don\u2019t Know?","volume-title":"Proc. ICLR","author":"Nalisnick"},{"key":"ref11","first-page":"20578","article-title":"Why Normalizing Flows Fail to Detect Out-of-distribution Data","volume-title":"Proc. NeurIPS","volume":"33","author":"Kirichenko"},{"key":"ref12","article-title":"Likelihood Ratios for Out-of-Distribution Detection","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref13","article-title":"Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models","volume-title":"Proc. ICLR","author":"Serr\u00e0"},{"key":"ref14","article-title":"Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality","author":"Nalisnick","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0844"},{"key":"ref18","first-page":"22528","article-title":"Unsupervised Out-of-distribution Detection with Diffusion Inpainting","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref19","article-title":"Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance","author":"Denouden","year":"2018"},{"key":"ref20","article-title":"Using Self-supervised Learning Can Improve Model Robustness and Uncertainty","volume-title":"Proc. NeurIPS","volume":"32","author":"Hendrycks"},{"key":"ref21","article-title":"Classification-Based Anomaly Detection for General Data","volume-title":"Proc. ICLR","author":"Bergman"},{"key":"ref22","first-page":"11839","article-title":"Csi: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","volume-title":"Proc. NeurIPS","volume":"33","author":"Tack"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/292"},{"key":"ref24","first-page":"20685","article-title":"Likelihood Regret: An Out-of-distribution Detection Score for Variational Auto-encoder","volume-title":"Proc. NeurIPS","volume":"33","author":"Xiao"},{"key":"ref25","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref26","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref27","article-title":"Score-based Generative Modeling in Latent Space","volume-title":"Proc. NeurIPS","author":"Vahdat"},{"key":"ref28","article-title":"Diffusion Models Beat GANs on Image Synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","article-title":"Elucidating the Design Space of Diffusion-Based Generative Models","volume-title":"Proc. NeurIPS","author":"Karras"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00152"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890879"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00076"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1525\/9780520313880-015"},{"key":"ref36","first-page":"181","article-title":"An Empirical Bayes Estimator of the Mean of a Normal Population","volume":"38","author":"Miyasawa","year":"1961","journal-title":"Bull. Inst. Internat. Statist."},{"key":"ref37","article-title":"Maximum Likelihood Training of Score-based Diffusion Models","volume-title":"Proc. NeurIPS","author":"Song"},{"key":"ref38","article-title":"Generalization in Diffusion Models Arises from Geometry-adaptive Harmonic Representations","volume-title":"Proc. ICLR","author":"Kadkhodaie"},{"key":"ref39","article-title":"Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models","author":"Shoushtari","year":"2025"},{"key":"ref40","article-title":"EigenScore: OOD Detection using Covariance in Diffusion Models","author":"Shoushtari","year":"2025"},{"key":"ref41","article-title":"On the Posterior Distribution in Denoising: Application to Uncertainty Quantification","volume-title":"Proc. ICLR","author":"Manor"},{"key":"ref42","article-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009","journal-title":"tech. rep., University of Toronto"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"}],"event":{"name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,29]]}},"container-title":["2025 59th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443114\/11443296\/11443828.pdf?arnumber=11443828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:26:10Z","timestamp":1774589170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf67917.2025.11443828","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}