{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:44:06Z","timestamp":1783737846277,"version":"3.55.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T00:00:00Z","timestamp":1685145600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Engineering Research Center Program through the National Research Foundation of Korea (NRF) funded by the Korean Government MSIT","award":["NRF-2018R1A5A1059921"],"award-info":[{"award-number":["NRF-2018R1A5A1059921"]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government","award":["2018-0-00769"],"award-info":[{"award-number":["2018-0-00769"]}]},{"name":"Luxembourg National Research Funds (FNR) through CORE project","award":["C18\/IS\/12669767\/STELLAR"],"award-info":[{"award-number":["C18\/IS\/12669767\/STELLAR"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>\n            The rapid and widespread adoption of Deep Neural Networks (DNNs) has called for ways to test their behaviour, and many testing approaches have successfully revealed misbehaviour of DNNs. However, it is relatively unclear what one can do to correct such behaviour after revelation, as retraining involves costly data collection and does not guarantee to fix the underlying issue. This article introduces Arachne, a novel program repair technique for DNNs, which directly repairs DNNs using their input-output pairs as a specification. Arachne localises neural weights on which it can generate effective patches and uses differential evolution to optimise the localised weights and correct the misbehaviour. An empirical study using different benchmarks shows that Arachne can fix specific misclassifications of a DNN without reducing general accuracy significantly. On average, patches generated by Arachne generalise to\n            <jats:styled-content style=\"color:#000000\">61.3%<\/jats:styled-content>\n            of unseen misbehaviour, whereas those by a state-of-the-art DNN repair technique generalise only to\n            <jats:styled-content style=\"color:#000000\">10.2% and sometimes to none while taking tens of times more than Arachne.<\/jats:styled-content>\n            We also show that Arachne can address fairness issues by debiasing a gender classification model.\n            <jats:styled-content style=\"color:#000000\">Finally, we successfully apply Arachne to a text sentiment model to show that it generalises beyond convolutional neural networks.<\/jats:styled-content>\n          <\/jats:p>","DOI":"10.1145\/3563210","type":"journal-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T14:12:41Z","timestamp":1663078361000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":60,"title":["Arachne: Search-Based Repair of Deep Neural Networks"],"prefix":"10.1145","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8093-2996","authenticated-orcid":false,"given":"Jeongju","family":"Sohn","sequence":"first","affiliation":[{"name":"University of Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0298-5320","authenticated-orcid":false,"given":"Sungmin","family":"Kang","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0836-6993","authenticated-orcid":false,"given":"Shin","family":"Yoo","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1001"},{"key":"e_1_3_2_7_2","first-page":"3104","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS\u201914)","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS\u201914). 3104\u20133112."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00108"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238187"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387940.3391456"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00043"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/2337223.2337225"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2874648"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00020"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2010.2059031"},{"key":"e_1_3_2_24_2","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:cs.LG\/1708.07747 (2017)."},{"key":"e_1_3_2_25_2","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"e_1_3_2_27_2","volume-title":"Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments","author":"Huang Gary B.","year":"2007","unstructured":"Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. 2007. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. Technical Report 07-49. University of Massachusetts, Amherst."},{"key":"e_1_3_2_28_2","unstructured":"Kaggle. [n.d.]. Twitter US Airline Sentiment. Retrieved September 18 2022 from https:\/\/www.kaggle.com\/datasets\/crowdflower\/twitter-airline-sentiment."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_30_2","article-title":"A survey on data collection for machine learning: A big data\u2013AI integration perspective","volume":"1811","author":"Roh Yuji","year":"2018","unstructured":"Yuji Roh, Geon Heo, and Steven Euijong Whang. 2018. A survey on data collection for machine learning: A big data\u2013AI integration perspective. CoRR abs\/1811.03402 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_31_2","first-page":"77","volume-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency. 77\u201391."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2521368"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070536"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554725"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2016.05.003"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380395"},{"key":"e_1_3_2_38_2","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"1409","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014).","journal-title":"CoRR"},{"key":"e_1_3_2_39_2","article-title":"MNIST handwritten digit database","author":"LeCun Yann","year":"2010","unstructured":"Yann LeCun, Corinna Cortes, and C. J. Burges. 2010. MNIST handwritten digit database. AT&T Labs [Online]. Retrieved September 18, 2022 from http:\/\/yann.lecun.com\/exdb\/mnist.","journal-title":"AT&T Labs [Online]"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.05.001"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2503311"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-63387-9_1","volume-title":"Computer Aided Verification","author":"Huang Xiaowei","year":"2017","unstructured":"Xiaowei Huang, Marta Kwiatkowska, Sen Wang, and Min Wu. 2017. Safety verification of deep neural networks. In Computer Aided Verification, Rupak Majumdar and Viktor Kun\u010dak (Eds.). Springer International, Cham, Switzerland, 3\u201329."},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/978-3-030-16722-6_10","volume-title":"Fundamental Approaches to Software Engineering","author":"Eniser Hasan Ferit","year":"2019","unstructured":"Hasan Ferit Eniser, Simos Gerasimou, and Alper Sen. 2019. DeepFault: Fault localization for deep neural networks. In Fundamental Approaches to Software Engineering, Reiner H\u00e4hnle and Wil van der Aalst (Eds.). Springer International, Cham, Switzerland, 171\u2013191."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180233"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563210","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:10Z","timestamp":1750178290000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,27]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3563210"],"URL":"https:\/\/doi.org\/10.1145\/3563210","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,27]]},"assertion":[{"value":"2021-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}