{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:28:53Z","timestamp":1729225733175,"version":"3.27.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>Accessing machine learning models through remote APIs has been gaining prevalence following the recent trend of scaling up model parameters for increased performance. Even though these models exhibit remarkable ability, detecting out-of-distribution (OOD) samples remains a crucial safety concern for end users as these samples may induce unreliable outputs from the model. In this work, we propose an OOD detection framework, MixDiff, that is applicable even when the model\u2019s parameters or its activations are not accessible to the end user. To bypass the access restriction, MixDiff applies an identical input-level perturbation to a given target sample and a similar in-distribution (ID) sample, then compares the relative difference in the model outputs of these two samples. MixDiff is model-agnostic and compatible with existing output-based OOD detection methods. We provide theoretical analysis to illustrate MixDiff\u2019s effectiveness in discerning OOD samples that induce overconfident outputs from the model and empirically demonstrate that MixDiff consistently enhances the OOD detection performance on various datasets in vision and text domains.<\/jats:p>","DOI":"10.3233\/faia240724","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:14:09Z","timestamp":1729170849000},"source":"Crossref","is-referenced-by-count":0,"title":["Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments"],"prefix":"10.3233","author":[{"given":"Heeyoung","family":"Lee","sequence":"first","affiliation":[{"name":"Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoyoon","family":"Byun","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changdae","family":"Oh","sequence":"additional","affiliation":[{"name":"University of Wisconsin\u2013Madison, Madison, Wisconsin, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JinYeong","family":"Bak","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungwoo","family":"Song","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:14:09Z","timestamp":1729170849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240724","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}