{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:39:33Z","timestamp":1759538373691,"version":"build-2065373602"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>Undetected out-of-distribution (OOD) inputs pose a significant threat to the reliability of deep learning models, as they may lead to unexpected behaviors during inference. Several studies have proposed effective OOD input detection methods. However, soft errors\u2014another significant threat to reliability\u2014can impact both the classification results of neural network models and the ID\/OOD detections of OOD detection methods. To provide a resilient OOD detection solution against soft errors, we analyze the effect of soft errors on neural network models with gradient-based input perturbation (GIP) approaches, which are representative methods for OOD detection. Building on our analysis, we propose ProGIP, which incorporates two software-level range-based fault detectors to protect all execution phases of GIP approaches, including two forward passes and one backward pass. Because it is purely software\u2011based and adds just two scalar comparisons, ProGIP is readily deployable even on resource\u2011constrained embedded platforms. Our ProGIP solution enables GIP approaches to distinguish between ID, OOD, and fault-affected inferences, detecting 97.7% of critical faults with a negligible runtime overhead of only 0.84%. Experimental results with 2.4 million fault injections across various neural networks and OOD detection methods demonstrate ProGIP\u2019s effectiveness in ensuring comprehensive reliability against non-malicious threats.<\/jats:p>","DOI":"10.1145\/3761796","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T11:51:58Z","timestamp":1756295518000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ProGIP: Protecting Gradient-based Input Perturbation Approaches for OOD Detection From Soft Errors"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8864-7575","authenticated-orcid":false,"given":"Sumedh Shridhar","family":"Joshi","sequence":"first","affiliation":[{"name":"Computer Science, Arizona State University","place":["Tempe, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3496-6079","authenticated-orcid":false,"given":"Hwisoo","family":"So","sequence":"additional","affiliation":[{"name":"Computer Department, Kyungpook National University","place":["Daegu, Korea (the Republic of)"]},{"name":"Department of Computer Science, Yonsei University","place":["Daegu, Korea (the Republic of)"]},{"name":"School of Computing and Augmented Intelligence, Arizona State University","place":["Daegu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8251-8028","authenticated-orcid":false,"given":"Soyeong","family":"Park","sequence":"additional","affiliation":[{"name":"Departmet of Computer Science, Yonsei University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8637-1333","authenticated-orcid":false,"given":"Woobin","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0741-1438","authenticated-orcid":false,"given":"Jinhyo","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9456-0927","authenticated-orcid":false,"given":"Yohan","family":"Ko","sequence":"additional","affiliation":[{"name":"Departmet of Computer Science, Yonsei University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5054-2236","authenticated-orcid":false,"given":"Uiwon","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ewha Womans University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5082-3775","authenticated-orcid":false,"given":"Kyoungwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University","place":["Seodaemun-gu, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1075-897X","authenticated-orcid":false,"given":"Aviral","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University","place":["Tempe, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10136985"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00018"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356177"},{"key":"e_1_3_2_6_2","unstructured":"Charles Corbi\u00e8re. 2022. Robust deep learning for autonomous driving. Ph.D. Dissertation. HESAM Universit\u00e9 Paris France. NNT: 2022HESAC032. tel-04351564f."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_8_2","unstructured":"Andrija Djurisic. 2022. Retrieved September 9 2025 from https:\/\/github.com\/andrijazz\/ash"},{"key":"e_1_3_2_9_2","unstructured":"Andrija Djurisic Nebojsa Bozanic Arjun Ashok and Rosanne Liu. 2023. Extremely simple activation shaping for out-of-distribution detection. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/arxiv.org\/abs\/2209.09858"},{"key":"e_1_3_2_10_2","unstructured":"Yicong Dong Rundong He Guangyao Chen Wentao Zhang Zhongyi Han Jieming Shi and Yilong Yin. 2025. G-OSR: A comprehensive benchmark for graph open-set recognition. arXiv:2503.00476. Retrieved from https:\/\/arxiv.org\/abs\/2503.00476"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.microrel.2010.08.016"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/IOLTS56730.2022.9897805"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774635"},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_15_2","first-page":"1321","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. 2017. On calibration of modern neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 1321\u20131330."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468784.3470655"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00033"},{"key":"e_1_3_2_19_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_20_2","unstructured":"Geoffrey E. Hinton Oriol Vinyals and Jeffrey Dean. 2014. Distilling the knowledge in a neural network. In Proceedings of NeurIPS 2014 Workshop on Deep Learning and Representation Learning. Retrieved from http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26741"},{"key":"e_1_3_2_24_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Master\u2019s thesis. University of Toronto Toronto Ontario."},{"key":"e_1_3_2_25_2","unstructured":"kuangliu. 2018. Retrieved September 9 2025 from https:\/\/github.com\/kuangliu\/pytorch-cifar\/blob\/master\/models\/mobilenetv2.py"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592144"},{"key":"e_1_3_2_27_2","unstructured":"CS Research Group led by Prof. Sharon Li. 2021. Retrieved September 9 2025 from https:\/\/github.com\/deeplearning-wisc\/react"},{"key":"e_1_3_2_28_2","unstructured":"Kimin Lee Kibok Lee Honglak Lee and Jinwoo Shin. 2018. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in Neural Information Processing Systems 31 (2018) 7167\u20137177."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126964"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSREW.2018.00024"},{"key":"e_1_3_2_31_2","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania et\u00a0al. 2020. Pytorch distributed: Experiences on accelerating data parallel training. arXiv:2006.15704. Retrieved from https:\/\/arxiv.org\/abs\/2006.15704"},{"key":"e_1_3_2_32_2","unstructured":"Yixuan Li. 2018. Retrieved Retrieved September 9 2025 from https:\/\/github.com\/facebookresearch\/odin"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Liang Shiyu","year":"2018","unstructured":"Shiyu Liang, Yixuan Li, and R. Srikant. 2018. Enhancing the reliability of out-of-distribution image detection in neural networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_34_2","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume":"33","author":"Liu Weitang","year":"2020","unstructured":"Weitang Liu, Xiaoyun Wang, John Owens, and Yixuan Li. 2020. Energy-based out-of-distribution detection. Advances in Neural Information Processing Systems 33 (2020), 21464\u201321475.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2005.37"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519563"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ATS47505.2019.000-8"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415680"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.34"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3052449"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294226"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99130-6_14"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643539"},{"key":"e_1_3_2_46_2","first-page":"144","article-title":"React: Out-of-distribution detection with rectified activations","volume":"34","author":"Sun Yiyou","year":"2021","unstructured":"Yiyou Sun, Chuan Guo, and Yixuan Li. 2021. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems 34 (2021), 144\u2013157.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09985-1"},{"key":"e_1_3_2_48_2","unstructured":"Sachin Vernekar Ashish Gaurav Vahdat Abdelzad Taylor Denouden Rick Salay and Krzysztof Czarnecki. 2019. Out-of-distribution detection in classifiers via generation. In NeurIPS 2019 Workshop on Safety and Robustness in Decision Making. Retrieved from https:\/\/arxiv.org\/abs\/1910.04241"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_34"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774562"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10050567"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Jingkang Yang Kaiyang Zhou Yixuan Li and Ziwei Liu. 2024. Generalized out-of-distribution detection: A survey. International Journal of Computer Vision 132 12 (2024) 5635\u20135662.","DOI":"10.1007\/s11263-024-02117-4"},{"key":"e_1_3_2_54_2","unstructured":"Jinsong Zhang Qiang Fu Xu Chen Lun Du Zelin Li Gang Wang XiaoGuang Liu Shi Han and Dongmei Zhang 2022. Out-of-distribution detection based on in-distribution data patterns memorization with modern Hopfield energy. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_55_2","unstructured":"Jingyang Zhang Jingkang Yang Pengyun Wang Haoqi Wang Yueqian Lin Haoran Zhang Yiyou Sun Xuefeng Du Yixuan Li Ziwei Liu Yiran Chen and Hai Li. 2024. OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection. Journal of Data-centric Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=cnnTnJQigsDatasetCertification"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01401"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3761796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T14:06:33Z","timestamp":1759500393000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3761796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":55,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3761796"],"URL":"https:\/\/doi.org\/10.1145\/3761796","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"assertion":[{"value":"2025-08-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}