{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:44:05Z","timestamp":1773384245424,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"UK Royal Academy of Engineering","award":["CiET17\/18-26"],"award-info":[{"award-number":["CiET17\/18-26"]}]},{"name":"DARPA Assured Autonomy programme","award":["FA8750-18- C-0095"],"award-info":[{"award-number":["FA8750-18- C-0095"]}]},{"name":"UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence","award":["EP\/S023356\/1"],"award-info":[{"award-number":["EP\/S023356\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3477314.3507059","type":"proceedings-article","created":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T00:37:36Z","timestamp":1651883856000},"page":"1031-1038","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Repairing misclassifications in neural networks using limited data"],"prefix":"10.1145","author":[{"given":"Patrick","family":"Henriksen","sequence":"first","affiliation":[{"name":"Imperial College London, London, United Kingdom"}]},{"given":"Francesco","family":"Leofante","sequence":"additional","affiliation":[{"name":"Imperial College London, London, United Kingdom"}]},{"given":"Alessio","family":"Lomuscio","sequence":"additional","affiliation":[{"name":"Imperial College London, London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR20)","author":"Akintunde M.","unstructured":"M. Akintunde, E. Botoeva, P. Kouvaros, and A. Lomuscio. 2020. Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems. In Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR20). IJCAI Press, 22--32."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-021-09529-3"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 32nd International Conference on Computer Aided Verification (CAV20)","volume":"12224","author":"Bak S.","unstructured":"S. Bak, H. Tran, K. Hobbs, and T. Johnson. 2020. Improved Geometric Path Enumeration for Verifying ReLU Neural Networks. In Proceedings of the 32nd International Conference on Computer Aided Verification (CAV20) (LNCS), Vol. 12224. Springer, 66--96."},{"key":"e_1_3_2_1_4_1","volume-title":"In proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI21)","author":"Battern B.","unstructured":"B. Battern, P. Kouvaros, A. Lomuscio, and Y. Zheng. 2021. Efficient neural network verification via layer-based semidefinite relaxations and linear cuts. In In proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI21). IJCAI, 2184--2190."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI20)","author":"Botoeva E.","unstructured":"E. Botoeva, P. Kouvaros, J. Kronqvist, A. Lomuscio, and R. Misener. 2020. Efficient Verification of Neural Networks via Dependency Analysis. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI20). AAAI Press."},{"key":"e_1_3_2_1_6_1","volume-title":"Advanced Lectures on Machine Learning (LNCS)","author":"Bottou L.","unstructured":"L. Bottou. 2003. Stochastic Learning. In Advanced Lectures on Machine Learning (LNCS), Vol. 3176. Springer, 146--168."},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"Branch and Bound for Piecewise Linear Neural Network Verification","volume":"21","author":"Bunel R.","year":"2020","unstructured":"R. Bunel, J. Lu, I. Turkaslan, P.H.S. Torr, P. Kohli, and M.P. Kumar. 2020. Branch and Bound for Piecewise Linear Neural Network Verification. Journal of Machine Learning Research (JMLR20) 21, 42 (2020), 1--39.","journal-title":"Journal of Machine Learning Research (JMLR20)"},{"key":"e_1_3_2_1_8_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE21)","author":"Cheng C.H","year":"2021","unstructured":"C.H Cheng. 2021. Provably-Robust Runtime Monitoring of Neuron Activation Patterns. In Design, Automation & Test in Europe Conference & Exhibition (DATE21). IEEE, 1310--1313."},{"key":"e_1_3_2_1_9_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE19)","author":"Cheng C.H.","unstructured":"C.H. Cheng, G. N\u00fchrenberg, and H. Yasuoka. 2019. Runtime Monitoring Neuron Activation Patterns. In Design, Automation & Test in Europe Conference & Exhibition (DATE19). IEEE, 300--303."},{"key":"e_1_3_2_1_10_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE21)","author":"Cheng C-H.","unstructured":"C-H. Cheng and R. Yan. 2021. Continuous Safety Verification of Neural Networks. In Design, Automation & Test in Europe Conference & Exhibition (DATE21). 1478--1483."},{"key":"e_1_3_2_1_11_1","unstructured":"A. De Palma R. Bunel A. Desmaison K. Dvijotham P. Kohli P. Torr and M. Kumar. 2021. Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition. arXiv preprint 2104.06718 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 27th International Joint Conference on Artificial Intelligence and 23rd European Conference on Artificial Intelligence (IJCAI-ECAI18)","author":"Dreossi T.","year":"2071","unstructured":"T. Dreossi, S. Ghosh, X. Yue, K. Keutzer, A. Sangiovanni-Vincentelli, and S. Seshia. 2018. Counterexample-guided data augmentation. In Proceedings of the 27th International Joint Conference on Artificial Intelligence and 23rd European Conference on Artificial Intelligence (IJCAI-ECAI18). AAAI press, 2071--2078."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 23th International Conference on Logic for Programming, Artificial Intelligence, and Reasoning (LPAR20)","volume":"73","author":"Goldberger B.","unstructured":"B. Goldberger, G. Katz, Y. Adi, and J. Keshet. 2020. Minimal Modifications of Deep Neural Networks using Verification. In Proceedings of the 23th International Conference on Logic for Programming, Artificial Intelligence, and Reasoning (LPAR20), Vol. 73. EasyChair, 260--278."},{"key":"e_1_3_2_1_14_1","unstructured":"A. Goodfellow Y. Bengio and A. Courville. 2016. Deep learning. MIT press Cambridge."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 16th International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR19)","volume":"11494","author":"Guidotti D.","unstructured":"D. Guidotti, F. Leofante, C. Castellini, and A. Tacchella. 2019. Repairing Learned Controllers with Convex Optimization: A Case Study. In Proceedings of the 16th International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR19), Vol. 11494. Springer, 364--373."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR16)","author":"He K.","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR16). IEEE Computer Society, 770--778."},{"key":"e_1_3_2_1_17_1","volume-title":"Bias Field Robustness Verification of Large Neural Image Classifiers. In In proceedings of the 32nd British Machine Vision Conference (BMVC21)","author":"Henriksen P.","unstructured":"P. Henriksen, K. Hammernik, D. Rueckert, and A. Lomuscio. 2021. Bias Field Robustness Verification of Large Neural Image Classifiers. In In proceedings of the 32nd British Machine Vision Conference (BMVC21)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 24th European Conference on Artificial Intelligence (ECAI20)","author":"Henriksen P.","unstructured":"P. Henriksen and A. Lomuscio. 2020. Efficient Neural Network Verification via Adaptive Refinement and Adversarial Search. In Proceedings of the 24th European Conference on Artificial Intelligence (ECAI20). IOS Press, 2513--2520."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21","author":"Henriksen P.","unstructured":"P. Henriksen and A. Lomuscio. 2021. DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. International Joint Conferences on Artificial Intelligence Organization, 2549--2555."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 24th European Conference on Artificial Intelligence (ECAI20)","author":"Henzinger T.A.","unstructured":"T.A. Henzinger, A. Lukina, and C. Schilling. 2020. Outside the Box: Abstraction-Based Monitoring of Neural Networks. In Proceedings of the 24th European Conference on Artificial Intelligence (ECAI20). IOS Press."},{"key":"e_1_3_2_1_21_1","unstructured":"G. Hinton. 2012. Lecture 6E. RMSprop: Divide the gradient by a running average of its recent magnitude. http:\/\/www.cs.toronto.edu\/tijmen\/csc321\/slides\/lecture_slides_lec6.pdf."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 32th International Conference on Machine Learning (ICML15)","author":"Ioffe S.","unstructured":"S. Ioffe and C. Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32th International Conference on Machine Learning (ICML15). JMLR.org, 448--456."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 31th International Conference on Computer Aided Verification (CAV19)","volume":"11561","author":"Katz G.","unstructured":"G. Katz, D. Huang, D. Ibeling, K. Julian, C. Lazarus, R. Lim, P. Shah, S. Thakoor, H. Wu, A. Zeljic, D. Dill, M. Kochenderfer, and C. Barrett. 2019. The Marabou Framework for Verification and Analysis of Deep Neural Networks. In Proceedings of the 31th International Conference on Computer Aided Verification (CAV19) (LNCS), Vol. 11561. Springer, 443--452."},{"key":"e_1_3_2_1_24_1","volume-title":"Formal Analysis of Neural Network-Based Systems in the Aircraft Domain. In International Symposium on Formal Methods (Lecture Notes in Computer Science)","volume":"13047","author":"Kouvaros P.","unstructured":"P. Kouvaros, T. Kyono, F. Leofante, A. Lomuscio, D. Margineantu, D. Osipychev, and Y. Zheng. 2021. Formal Analysis of Neural Network-Based Systems in the Aircraft Domain. In International Symposium on Formal Methods (Lecture Notes in Computer Science), Vol. 13047. Springer, 730--740."},{"key":"e_1_3_2_1_25_1","unstructured":"P. Kouvaros and A. Lomuscio. 2018. Formal Verification of CNN-based Perception Systems. arXiv preprint arXiv:1811.11373 (2018)."},{"key":"e_1_3_2_1_26_1","volume-title":"In proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI21)","author":"Kouvaros P.","unstructured":"P. Kouvaros and A. Lomuscio. 2021. Towards scalable complete verification of relu neural networks via dependency-based branching. In In proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI21). IJCAI, 2643--2650."},{"key":"e_1_3_2_1_28_1","volume-title":"Proccedings of the 36th AAAI Conference on Artificial Intelligence (AAAI22)","author":"Lan J.","unstructured":"J. Lan, A. Lomuscio, and Y. Zheng. 2021. Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations.. In Proccedings of the 36th AAAI Conference on Artificial Intelligence (AAAI22). AAAI Press, To appear."},{"key":"e_1_3_2_1_29_1","unstructured":"Y. Lecun. 1999. THE MNIST DATABASE of handwritten digits. https:\/\/ci.nii.ac.jp\/naid\/10027939599\/en\/."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2018 ACM Symposium on the Foundations of Software Engineering FSE18","author":"Ma S.","unstructured":"S. Ma, Y. Liu, W. Lee, X. Zhang, and A. Grama. 2018. MODE: automated neural network model debugging via state differential analysis and input selection. In Proceedings of the 2018 ACM Symposium on the Foundations of Software Engineering FSE18. ACM, 175--186."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 22nd International Conference on Computer Aided Verification (CAV10)","volume":"6184","author":"Pulina L.","unstructured":"L. Pulina and A. Tacchella. 2010. An Abstraction-Refinement Approach to Verification of Artificial Neural Networks. In Proceedings of the 22nd International Conference on Computer Aided Verification (CAV10) (LNCS), Vol. 6184. Springer, 243--257."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 14th IEEE International Conference on Machine Learning and Applications (ICMLA'15)","author":"Ribeiro M.","unstructured":"M. Ribeiro, K. Grolinger, and M. Capretz. 2015. MLaaS: Machine Learning as a Service. In Proceedings of the 14th IEEE International Conference on Machine Learning and Applications (ICMLA'15). IEEE, 896--902."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML18)","volume":"80","author":"Serra T.","unstructured":"T. Serra, C. Tjandraatmadja, and S. Ramalingam. 2018. Bounding and Counting Linear Regions of Deep Neural Networks. In Proceedings of the 35th International Conference on Machine Learning (ICML18) (PMLR), Vol. 80. PMLR, 4565--4573."},{"key":"e_1_3_2_1_34_1","volume-title":"proceedings of the ACM on Programming Languages 3, POPL","author":"Singh G.","year":"2019","unstructured":"G. Singh, T. Gehr, M. P\u00fcschel, and M. Vechev. 2019. An abstract domain for certifying neural networks. In proceedings of the ACM on Programming Languages 3, POPL (2019), 41."},{"key":"e_1_3_2_1_35_1","unstructured":"J. Sohn S. Kang and S. Yoo. 2019. Search Based Repair of Deep Neural Networks. arXiv preprint 1912.12463 (2019)."},{"key":"e_1_3_2_1_36_1","volume-title":"Generalizing Patches. In Workshop on Safety and Robustness in Decision Making.","author":"Sotoudeh M.","unstructured":"M. Sotoudeh and A. Thakur. 2019. Correcting Deep Neural Networks with Small, Generalizing Patches. In Workshop on Safety and Robustness in Decision Making."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 41st International Conference on Software Engineering: Companion Proceedings, ICSE 2019, Montreal, QC, Canada, May 25--31","author":"Sun Y.","year":"2019","unstructured":"Y. Sun, X. Huang, D. Kroening, J. Sharp, M. Hill, and R. Ashmore. 2019. Deep-Concolic: testing and debugging deep neural networks. In Proceedings of the 41st International Conference on Software Engineering: Companion Proceedings, ICSE 2019, Montreal, QC, Canada, May 25--31, 2019. IEEE \/ ACM, 111--114."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 41st International Conference on Software Engineering: Companion Proceedings, ICSE 2019, Montreal, QC, Canada, May 25--31","author":"Sun Y.","year":"2019","unstructured":"Y. Sun, X. Huang, D. Kroening, J. Sharp, M. Hill, and R. Ashmore. 2019. Structural test coverage criteria for deep neural networks. In Proceedings of the 41st International Conference on Software Engineering: Companion Proceedings, ICSE 2019, Montreal, QC, Canada, May 25--31, 2019. IEEE \/ ACM, 320--321."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 32rd International Conference on Computer Aided Verification (CAV20)","volume":"12224","author":"Tran H.","unstructured":"H. Tran, X. Yang, D. Manzanas Lopez, P. Musau, L. Nguyen, W. Xiang, S. Bak, and T. Johnson. 2020. NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems. In Proceedings of the 32rd International Conference on Computer Aided Verification (CAV20) (LNCS), Vol. 12224. Springer, 3--17."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 33rd International Conference on Computer Aided Verification (CAV21)","volume":"12759","author":"Usman M.","unstructured":"M. Usman, D. Gopinath, Y. Sun, Y. Noller, and C. Pasareanu. 2021. NNrepair: Constraint-Based Repair of Neural Network Classifiers. In Proceedings of the 33rd International Conference on Computer Aided Verification (CAV21) (LNCS), Vol. 12759. Springer, 3--25."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 31st Annual Conference on Neural Information Processing Systems 2018 (NeurIPS2018)","author":"Wang S.","unstructured":"S. Wang, K. Pei, J. Whitehouse, J. Yang, and S. Jana. 2018. Efficient Formal Safety Analysis of Neural Networks. In Proceedings of the 31st Annual Conference on Neural Information Processing Systems 2018 (NeurIPS2018). Curran Associates, Inc., 6367--6377."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 27th USENIX Security Symposium (USENIX18)","author":"Wang S.","unstructured":"S. Wang, K. Pei, J. Whitehouse, J. Yang, and S. Jana. 2018. Formal Security Analysis of Neural Networks using Symbolic Intervals. In Proceedings of the 27th USENIX Security Symposium (USENIX18)."},{"key":"e_1_3_2_1_43_1","unstructured":"S. Wang H. Zhang K. Xu X. Lin S. Jana C. Hsieh and Z. Kolter. 2021. Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Verification. arXiv preprint 2103.06624 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE19)","author":"Zhang H.","unstructured":"H. Zhang and W. K. Chan. 2019. Apricot: A Weight-Adaptation Approach to Fixing Deep Learning Models. In Proceedings of the 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE19). IEEE, 376--387."}],"event":{"name":"SAC '22: The 37th ACM\/SIGAPP Symposium on Applied Computing","location":"Virtual Event","acronym":"SAC '22","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507059","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477314.3507059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:28Z","timestamp":1750188688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":43,"alternative-id":["10.1145\/3477314.3507059","10.1145\/3477314"],"URL":"https:\/\/doi.org\/10.1145\/3477314.3507059","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}