{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:57:27Z","timestamp":1769727447812,"version":"3.49.0"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R & D Program of China","doi-asserted-by":"crossref","award":["2022YFA1005101"],"award-info":[{"award-number":["2022YFA1005101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61872371 and 62032024"],"award-info":[{"award-number":["61872371 and 62032024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>\n            Neural networks are important computational models used in the domains of artificial intelligence and software engineering. Parameters of a neural network are obtained via training it against a specific dataset with a standard process, which guarantees each sample within that set is mapped to the correct class. In general, for a trained neural network, there is no warranty of high-level properties, such as fairness, robustness, and so forth. In this case, one need to tune the parameters in an alternative manner, and it is called repairing. In this paper, we present AutoRIC (\n            <jats:italic>Auto<\/jats:italic>\n            mated\n            <jats:italic>R<\/jats:italic>\n            epair w\n            <jats:italic>I<\/jats:italic>\n            th\n            <jats:italic>C<\/jats:italic>\n            onstraints), an analytical-approach-based white-box repairing framework against general properties that could be quantitatively measured. Our approach is mainly based on constrained optimization, namely, we treat the properties of neural network as the optimized objective described by a quadratic formula about the faulty parameters. To ensure the classification accuracy of the repaired neural network, we impose linear inequality constraints to the inputs that obtain incorrect outputs from the neural network. In general, this may generate a huge amount of constraints, resulting in the prohibitively high cost in the problem solving, or even making the problem unable to be solved by the constraint solver. To circumvent this, we present a selection strategy to diminish the restrictions, i.e., we always select the most \u2018strict\u2019 ones into the constraint set each time. Experimental results show that repairing with constraints performs efficiently and effectively. AutoRIC tends to achieve a satisfactory repairing result whereas brings in a negligible accuracy drop. AutoRIC enjoys a notable time advantage and this advantage becomes increasingly evident as the network complexity rises. Moreover, experiment results also demonstrate that repairing based on unconstrained optimizations are not stable, which embodies the necessity of constraints.\n          <\/jats:p>","DOI":"10.1145\/3690634","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:23:09Z","timestamp":1725474189000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["AutoRIC: Automated Neural Network Repairing Based on Constrained Optimization"],"prefix":"10.1145","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5272-3230","authenticated-orcid":false,"given":"Xinyu","family":"Sun","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2315-1704","authenticated-orcid":false,"given":"Wanwei","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1469-2063","authenticated-orcid":false,"given":"Shangwen","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4833-2177","authenticated-orcid":false,"given":"Tingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1478-9144","authenticated-orcid":false,"given":"Ye","family":"Tao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4204-7424","authenticated-orcid":false,"given":"Xiaoguang","family":"Mao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,1,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012412"},{"key":"e_1_3_1_3_2","unstructured":"Aniya Aggarwal Pranay Lohia Seema Nagar Kuntal Dey and Diptikalyan Saha. 2018. Automated test generation to detect individual discrimination in AI Models. CoRR abs\/1809.03260 (2018). arXiv:1809.03260. Retrieved from http:\/\/arxiv.org\/abs\/1809.03260"},{"key":"e_1_3_1_4_2","first-page":"11","article-title":"Evaluating and improving unified debugging","volume":"48","author":"Benton Samuel","year":"2021","unstructured":"Samuel Benton, Xia Li, Yiling Lou, and Lingming Zhang. 2021. Evaluating and improving unified debugging. IEEE Transactions on Software Engineering 48, 11 (2021), 4692\u20134716.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"M. A. Bhatti. 2000. Practical Optimization Methods With Mathematica Applications. Springer.","DOI":"10.1007\/978-1-4612-0501-2"},{"key":"e_1_3_1_6_2","first-page":"2712","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Boetius David","year":"2023","unstructured":"David Boetius, Stefan Leue, and Tobias Sutter. 2023. A robust optimisation perspective on counterexample-guided repair of neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 2712\u20132737."},{"key":"e_1_3_1_7_2","unstructured":"Mariusz Bojarski Davide Del Testa Daniel Dworakowski Bernhard Firner Beat Flepp Prasoon Goyal Lawrence D. Jackel Mathew Monfort Urs Muller Jiakai Zhang Xin Zhang Jake Zhao and Karol Zieba. 2016. End to end learning for self-driving cars."},{"key":"e_1_3_1_8_2","unstructured":"Cjadams Jeffrey Sorensen Julia Elliott Lucas Dixon Mark McDonald nithum and Will Cukierski. 2017. Toxic Comment Classification Challenge. Retrieved from https:\/\/kaggle.com\/competitions\/jigsaw-toxic-comment-classification-challenge"},{"key":"e_1_3_1_9_2","volume-title":"Linear Programming and Extensions","author":"Dantzig G. B.","year":"1963","unstructured":"G. B. Dantzig. 1963. Linear Programming and Extensions. Princeton University Press."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468507.3468513"},{"key":"e_1_3_1_11_2","volume-title":"Interior Point Approach to Linear, Quadratic and Convex Programming","author":"Hertog D. den","year":"1993","unstructured":"D. den Hertog. 1993. Interior Point Approach to Linear, Quadratic and Convex Programming. Kluwer."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16722-6_10"},{"key":"e_1_3_1_13_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Fu Feisi","year":"2021","unstructured":"Feisi Fu and Wenchao Li. 2021. Sound and complete neural network repair with minimality and locality guarantees. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_14_2","first-page":"921","volume-title":"Proceedings of the 44th International Conference on Software Engineering","author":"Gao Xuanqi","year":"2022","unstructured":"Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, and Qian Wang. 2022. FairNeuron: Improving deep neural network fairness with adversary games on selective neurons. In Proceedings of the 44th International Conference on Software Engineering, 921\u2013933."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3317950"},{"key":"e_1_3_1_16_2","first-page":"260","volume-title":"Proceedings of the 23rd International Conference on Logic for Programming, Artificial Intelligence and Reasoning (LPAR \u201920)","volume":"2020","author":"Goldberger Ben","year":"2020","unstructured":"Ben Goldberger, Guy Katz, Yossi Adi, and Joseph Keshet. 2020. Minimal modifications of deep neural networks using verification. In Proceedings of the 23rd International Conference on Logic for Programming, Artificial Intelligence and Reasoning (LPAR \u201920), Vol. 2020, 260\u2013278."},{"key":"e_1_3_1_17_2","unstructured":"Richard Gonzales. 2020. Feds Say Self-Driving Uber Suv did not Recognize Jaywalking Pedestrian in Fatal Crash. NPR Retrieved from https:\/\/www.npr.org\/2019\/11\/07\/777438412\/feds-say-self-driving-uber-suv-did-not-recognize-jaywalking-pedestrian-in-fatal-(Nov 2019)"},{"key":"e_1_3_1_18_2","article-title":"Facebook translates\u2019 good morning\u2019into\u2019attack them\u2019, leading to arrest","volume":"24","author":"Hern Alex","year":"2017","unstructured":"Alex Hern. 2017. Facebook translates\u2019 good morning\u2019into\u2019attack them\u2019, leading to arrest. The Guardian 24 (2017).","journal-title":"The Guardian"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1201\/9781003278290-21","volume-title":"Ethics of Data and Analytics","author":"Hill Kashmir","year":"2022","unstructured":"Kashmir Hill. 2022. Wrongfully accused by an algorithm. In Ethics of Data and Analytics. Auerbach Publications, 138\u2013142."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.2514\/1.G003724"},{"key":"e_1_3_1_21_2","first-page":"4171","volume-title":"Proceedings of the NAACL-HLT","author":"Kenton Jacob Devlin Ming-Wei Chang","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the NAACL-HLT, 4171\u20134186."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Ron Kohavi. 1996. Census income. DOI: 10.24432\/C5GP7S","DOI":"10.24432\/C5GP7S"},{"key":"e_1_3_1_24_2","first-page":"25","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 25.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_1_27_2","unstructured":"Zhen Liang Taoran Wu Changyuan Zhao Wanwei Liu Bai Xue Wenjing Yang and Ji Wang. 2023. Repairing deep neural networks based on behavior imitation. arXiv:2305.03365 [cs.LG]"},{"key":"e_1_3_1_28_2","first-page":"1","volume-title":"Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering","author":"Ma Jianan","year":"2024","unstructured":"Jianan Ma, Pengfei Yang, Jingyi Wang, Youcheng Sun, Cheng-Chao Huang, and Zhen Wang. 2024. VeRe: Verification guided synthesis for repairing deep neural networks. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, 1\u201313."},{"key":"e_1_3_1_29_2","first-page":"100","volume-title":"Proceedings of the IEEE 29th International Symposium on Software Reliability Engineering (ISSRE \u201918)","author":"Ma Lei","unstructured":"Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, and Yadong Wang. Deepmutation: Mutation testing of deep learning systems. In Proceedings of the IEEE 29th International Symposium on Software Reliability Engineering (ISSRE \u201918), IEEE, 100\u2013111."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"e_1_3_1_31_2","unstructured":"Keyvan Majd Siyu Zhou Heni Ben Amor Georgios Fainekos and Sriram Sankaranarayanan. 2021. Local repair of neural networks using optimization. arXiv:2109.14041."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","unstructured":"S\u00e9rgio Moro Paulo Rita and Paulo Cortez. 2012. Bank marketing. DOI: 10.24432\/C5K306","DOI":"10.24432\/C5K306"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Long H. Pham Jiaying Li and Jun Sun. 2020. SOCRATES: Towards a unified platform for neural network analysis. arXiv:2007.11206. Retrieved from 10.48550\/arXiv.2007.11206","DOI":"10.48550\/arXiv.2007.11206"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173"},{"key":"e_1_3_1_36_2","first-page":"10825","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems (NeurIPS \u201918)","author":"Singh Gagandeep","year":"2018","unstructured":"Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus P\u00fcschel, and Martin T. Vechev. 2018. Fast and effective robustness certification. In Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems (NeurIPS \u201918). Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.), 10825\u201310836. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/f2f446980d8e971ef3da97af089481c3-Abstract.html"},{"key":"e_1_3_1_37_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Sinitsin Anton","year":"2019","unstructured":"Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitry Pyrkin, Sergei Popov, and Artem Babenko. 2019. Editable neural networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563210"},{"key":"e_1_3_1_39_2","first-page":"98","volume-title":"Proceedings of the IEEE\/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion \u201923)","author":"Song Xidan","year":"2023","unstructured":"Xidan Song, Youcheng Sun, Mustafa A. Mustafa, and Lucas C. Cordeiro. 2023. Airepair: A repair platform for neural networks. In Proceedings of the IEEE\/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion \u201923). IEEE, 98\u2013101."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454064"},{"key":"e_1_3_1_41_2","first-page":"83","volume-title":"Proceedings of the 24th International Symposium on Formal Methods (FM \u201921)","author":"Sun Bing","year":"2021","unstructured":"Bing Sun, Jun Sun, Ting Dai, and Lijun Zhang. 2021. Probabilistic verification of neural networks against group fairness. In Proceedings of the 24th International Symposium on Formal Methods (FM \u201921). Springer, 83\u2013102."},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510080"},{"key":"e_1_3_1_43_2","first-page":"443","volume-title":"Proceedings of the ACM on Programming Languages","volume":"7","author":"Tao Zhe","year":"2023","unstructured":"Zhe Tao, Stephanie Nawas, Jacqueline Mitchell, and Aditya V. Thakur. 2023. Architecture-preserving provable repair of deep neural networks. Proceedings of the ACM on Programming Languages 7, PLDI (2023), 443\u2013467."},{"key":"e_1_3_1_44_2","first-page":"66","volume-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering (ICSE \u201923)","author":"Tianlin Li","year":"2023","unstructured":"Li Tianlin, Cao Yue, Zhang Jian, Zhao Shiqian, Huang Yihao, Liu Aishan, Guo Qing, and Liu Yang. 2023. RUNNER: Responsible UNfair NEuron repair for enhancing deep neural network fairness. In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering (ICSE \u201923). IEEE Computer Society, 66\u201378."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/EUROSP.2017.29"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238165"},{"key":"e_1_3_1_47_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-81685-8_1","volume-title":"Proceedings of the 33rd International Conference on Computer Aided Verification (CAV \u201921)","author":"Usman Muhammad","year":"2021","unstructured":"Muhammad Usman, Divya Gopinath, Youcheng Sun, Yannic Noller, and Corina S. P\u0103s\u0103reanu. 2021. Nn repair: Constraint-based repair of neural network classifiers. In Proceedings of the 33rd International Conference on Computer Aided Verification (CAV \u201921). Springer, 3\u201325."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1142\/S1793962323410088"},{"key":"e_1_3_1_49_2","first-page":"11383","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xie Xiaofei","year":"2021","unstructured":"Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Lingjun Zhou, Yang Liu, and Xinyu Xing. 2021. RNNrepair: Automatic RNN repair via model-based analysis. In Proceedings of the International Conference on Machine Learning. PMLR, 11383\u201311392."},{"key":"e_1_3_1_50_2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/978-3-031-15839-1_13","volume-title":"Proceedings of the International Conference on Formal Modeling and Analysis of Timed Systems","author":"Yang Xiaodong","year":"2022","unstructured":"Xiaodong Yang, Tom Yamaguchi, Hoang-Dung Tran, Bardh Hoxha, Taylor T. Johnson, and Danil Prokhorov. 2022. Neural network repair with reachability analysis. In Proceedings of the International Conference on Formal Modeling and Analysis of Timed Systems. Springer, 221\u2013236."},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3096332"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380331"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690634","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:10Z","timestamp":1750295950000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690634"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3690634"],"URL":"https:\/\/doi.org\/10.1145\/3690634","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2024-02-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}