{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:38:51Z","timestamp":1791459531640,"version":"4.3.4"},"reference-count":101,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>Although Deep Neural Networks (DNNs) have achieved significant success across various industries, their erroneous behaviors have raised widespread concerns. In safety-critical domains where DNNs are deployed, certain types of specific misclassifications (i.e., instances of one specific class being misclassified as another) can lead to catastrophic consequences and urgently need to be corrected. However, existing repair approaches often neglect the adverse impact of general feature extraction patterns on distinguishing specific classes, resulting in limited correction of specific misclassifications. Furthermore, most approaches correct errors by directly adjusting the global decision boundary, which inevitably disturbs the well-trained boundaries and leads to significant accuracy loss.<\/jats:p>\n                  <jats:p>\n                    In this article, we propose SMiR, an effective repair framework for addressing specific misclassifications with marginal accuracy loss. Rather than patching the original model, our method localizes and recovers the distorted feature dimensions to mitigate their negative impact on the distinction between specific classes. Moreover, SMiR narrows the scope of repair to the filtered suspect set, protecting other well-trained decision boundaries from disturbance. On average, our approach repairs 27%\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\sim\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    36.2% more specific misclassifications than the baselines, while introducing only 7.8%\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\sim\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    70.9% as many new errors. Besides, SMiR maintains state-of-the-art performance on safety-critical datasets.\n                  <\/jats:p>","DOI":"10.1145\/3771545","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T15:36:39Z","timestamp":1760456199000},"page":"1-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SMiR: Minimizing Side Effects in Repairing Specific Misclassifications for Deep Neural Networks"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8290-8167","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"first","affiliation":[{"name":"School of Reliability and Systems Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0241-0009","authenticated-orcid":false,"given":"Shihai","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1991-360X","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6203-2713","authenticated-orcid":false,"given":"Tengfei","family":"Shi","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2808-3642","authenticated-orcid":false,"given":"Wentao","family":"Wu","sequence":"additional","affiliation":[{"name":"China Northern Vehicle Research Institute, Beijing, China and Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4457-114X","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"2549","volume-title":"International Conference on Machine Learning","author":"Almahairi Amjad","year":"2016","unstructured":"Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, and Aaron Courville. 2016. Dynamic capacity networks. In International Conference on Machine Learning. PMLR, 2549\u20132558."},{"key":"e_1_3_1_3_2","first-page":"1","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi Laith","year":"2021","unstructured":"Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al-Dujaili, Ye Duan, Omran Al-Shamma, Jos\u00e9 Santamar\u00eda, Mohammed A. Fadhel, Muthana Al-Amidie, and Laith Farhan. 2021. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data 8 (2021), 1\u201374.","journal-title":"Journal of Big Data"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809163","volume-title":"Introduction to Software Testing","author":"Ammann Paul","year":"2008","unstructured":"Paul Ammann and Jeff Offutt. 2008. Introduction to Software Testing. Cambridge University Press, New York."},{"key":"e_1_3_1_5_2","unstructured":"Anonymous. 2024. Open-Source Code of SMiR. Retrieved from https:\/\/github.com\/AnonymousSE4AI\/SMiR"},{"key":"e_1_3_1_6_2","unstructured":"Apple. 2023. ml-fastvit. Retrieved from https:\/\/github.com\/apple\/ml-fastvit"},{"key":"e_1_3_1_7_2","unstructured":"bennythedataguy. 2016. Order of Weights in LSTM. Retrieved from https:\/\/github.com\/keras-team\/keras\/issues\/3088"},{"issue":"4","key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1007\/s42979-024-02717-4","article-title":"Clustering based undersampling for effective learning from imbalanced data: An iterative approach","volume":"5","author":"Bhattacharya Rajdeep","year":"2024","unstructured":"Rajdeep Bhattacharya, Rajonya De, Anuran Chakraborty, and Ram Sarkar. 2024. Clustering based undersampling for effective learning from imbalanced data: An iterative approach. SN Computer Science 5, 4 (2024), 386.","journal-title":"SN Computer Science"},{"key":"e_1_3_1_9_2","first-page":"88","volume-title":"2021 IEEE 4th International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","author":"Bokhari Wasif","year":"2021","unstructured":"Wasif Bokhari, James Smith, and Ajay Bansal. 2021. Multi-class classification with asymmetric error control for medical disease diagnosis. In 2021 IEEE 4th International Conference on Artificial Intelligence and Knowledge Engineering (AIKE). IEEE, 88\u201394."},{"key":"e_1_3_1_10_2","first-page":"573","volume-title":"44th International Conference on Software Engineering","author":"Cao Jialun","year":"2022","unstructured":"Jialun Cao, Meiziniu Li, Xiao Chen, Ming Wen, Yongqiang Tian, Bo Wu, and Shing-Chi Cheung. 2022. Deepfd: Automated fault diagnosis and localization for deep learning programs. In 44th International Conference on Software Engineering, 573\u2013585."},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla Nitesh V.","year":"2002","unstructured":"Nitesh V. Chawla, Kevin W. Bowyer, Lawrence O. Hall, and W. Philip Kegelmeyer. 2002. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research 16 (2002), 321\u2013357.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"e_1_3_1_12_2","first-page":"1","volume-title":"ACM Transactions on Software Engineering and Methodology","author":"Chen Jialuo","year":"2022","unstructured":"Jialuo Chen, Jingyi Wang, Xingjun Ma, Youcheng Sun, Jun Sun, Peixin Zhang, and Peng Cheng. 2022. QuoTe: Quality-oriented Testing for Deep Learning Systems. ACM Transactions on Software Engineering and Methodology 32, 5 (2022), 1\u201333."},{"key":"e_1_3_1_13_2","first-page":"9268","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cui Yin","year":"2019","unstructured":"Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9268\u20139277."},{"key":"e_1_3_1_14_2","unstructured":"Lindsay Curtis. 2022. Misdiagnosed Lung Cancer and the Cost of Diagnosis Delays. Retrieved from https:\/\/www.verywellhealth.com\/risks-of-misdiagnosed-lung-cancer-and-delayed-treatment-5248414"},{"issue":"5","key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s10664-024-10515-y","article-title":"Towards exploring the limitations of test selection techniques on graph neural networks: An empirical study","volume":"29","author":"Dang Xueqi","year":"2024","unstructured":"Xueqi Dang, Yinghua Li, Wei Ma, Yuejun Guo, Qiang Hu, Mike Papadakis, Maxime Cordy, and Yves Le Traon. 2024. Towards exploring the limitations of test selection techniques on graph neural networks: An empirical study. Empirical Software Engineering 29, 5 (2024), 112.","journal-title":"Empirical Software Engineering"},{"issue":"1","key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3607191","article-title":"Graphprior: Mutation-based test input prioritization for graph neural networks","volume":"33","author":"Dang Xueqi","year":"2023","unstructured":"Xueqi Dang, Yinghua Li, Mike Papadakis, Jacques Klein, Tegawend\u00e9 F. Bissyand\u00e9, and Yves Le Traon. 2023. Graphprior: Mutation-based test input prioritization for graph neural networks. ACM Transactions on Software Engineering and Methodology 33, 1 (2023), 1\u201340.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_17_2","volume-title":"A Probabilistic Theory of Pattern Recognition","author":"Devroye Luc","year":"2013","unstructured":"Luc Devroye, L\u00e1szl\u00f3 Gy\u00f6rfi, and G\u00e1bor Lugosi. 2013. A Probabilistic Theory of Pattern Recognition, Vol. 31. Springer Science & Business Media."},{"key":"e_1_3_1_18_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_1_19_2","first-page":"2739","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Duarte Kevin","year":"2021","unstructured":"Kevin Duarte, Yogesh Rawat, and Mubarak Shah. 2021. Plm: Partial label masking for imbalanced multi-label classification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2739\u20132748."},{"key":"e_1_3_1_20_2","unstructured":"Figure Eight. 2020. Twitter US Airline Sentiment. Retrieved from https:\/\/www.kaggle.com\/datasets\/crowdflower\/twitter-airline-sentiment"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1109\/ATSIP62566.2024.10638849","volume-title":"2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP)","volume":"1","author":"Elmangoush Abdullah M.","year":"2024","unstructured":"Abdullah M. Elmangoush, Hanein O. Hassan, Ayyah A. Fadhl, and Malak Ahmed Alshrif. 2024. Credit card fraud detection using synthetic minority oversampling technique and deep learning technique. In 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP), Vol. 1. IEEE, 455\u2013458."},{"key":"e_1_3_1_22_2","first-page":"1625","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Eykholt Kevin","year":"2018","unstructured":"Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, and Dawn Song. 2018. Robust physical-world attacks on deep learning visual classification. In IEEE Conference on Computer Vision and Pattern Recognition, 1625\u20131634."},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Scott Freitas Jovan Kalajdjieski Amir Gharib and Robert McCann. 2024. AI-driven guided response for security operation centers with Microsoft Copilot for security. arXiv:2407.09017. Retrieved from https:\/\/arxiv.org\/abs\/2407.09017","DOI":"10.1145\/3701716.3715209"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5788-0_64"},{"key":"e_1_3_1_25_2","unstructured":"Tianyu Gu Brendan Dolan-Gavitt and Siddharth Garg. 2017. Badnets: Identifying vulnerabilities in the machine learning model supply chain. arXiv:1708.06733. Retrieved from https:\/\/arxiv.org\/abs\/1708.06733"},{"issue":"2","key":"e_1_3_1_26_2","first-page":"933","article-title":"Coverage guided differential adversarial testing of deep learning systems","volume":"8","author":"Guo Jianmin","year":"2020","unstructured":"Jianmin Guo, Yue Zhao, Houbing Song, and Yu Jiang. 2020. Coverage guided differential adversarial testing of deep learning systems. IEEE Transactions on Network Science and Engineering 8, 2 (2020), 933\u2013942.","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"e_1_3_1_27_2","first-page":"770","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, NV, 770\u2013778. DOI: 10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_28_2","unstructured":"Md Sazzad Hossain Andrew P. Paplinski and John M. Betts. 2019. Adaptive class weight based dual focal loss for improved semantic segmentation. arXiv:1909.11932. Retrieved from https:\/\/arxiv.org\/abs\/1909.11932"},{"key":"e_1_3_1_29_2","first-page":"13410","volume-title":"International Conference on Machine Learning","author":"Hounie Ignacio","year":"2023","unstructured":"Ignacio Hounie, Luiz F. O. Chamon, and Alejandro Ribeiro. 2023. Automatic data augmentation via invariance-constrained learning. In International Conference on Machine Learning. PMLR, 13410\u201313433."},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1109\/ICSE48619.2023.00093","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE)","author":"Imtiaz Sayem Mohammad","year":"2023","unstructured":"Sayem Mohammad Imtiaz, Fraol Batole, Astha Singh, Rangeet Pan, Breno Dantas Cruz, and Hridesh Rajan. 2023. Decomposing a recurrent neural network into modules for enabling reusability and replacement. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 1020\u20131032."},{"key":"e_1_3_1_31_2","unstructured":"irem nur tokuroglu. 2025. Credit Score Classification ANN. Retrieved from https:\/\/www.kaggle.com\/code\/iremnurtokuroglu\/credit-score-classification-ann-90-86-accuracy\/notebook"},{"key":"e_1_3_1_32_2","unstructured":"irem nur tokuroglu. 2025. Credit Score Classification Cleaned Dataset. Retrieved from https:\/\/www.kaggle.com\/datasets\/iremnurtokuroglu\/credit-score-classification-cleaned-dataset\/data"},{"key":"e_1_3_1_33_2","unstructured":"Isa. 2019. How to Interpret Weights in a LSTM Layer in Keras. Retrieved from https:\/\/stackoverflow.com\/questions\/42861460\/how-to-interpret-weights-in-a-lstm-layer-in-keras"},{"issue":"4","key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3702983","article-title":"Repairs and breaks prediction for deep neural networks","volume":"34","author":"Ishimoto Yuta","year":"2025","unstructured":"Yuta Ishimoto, Masanari Kondo, Lei Ma, Naoyasu Ubayashi, and Yasutaka Kamei. 2025. Repairs and breaks prediction for deep neural networks. ACM Transactions on Software Engineering and Methodology 34, 4 (2025), 1\u201342.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_35_2","unstructured":"Md Amirul Islam Matthew Kowal Patrick Esser Sen Jia Bjorn Ommer Konstantinos G. Derpanis and Neil Bruce. 2021. Shape or texture: Understanding discriminative features in cnns. arXiv:2101.11604. Retrieved from https:\/\/arxiv.org\/abs\/2101.11604"},{"key":"e_1_3_1_36_2","first-page":"1","volume-title":"2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","author":"Jadon Shruti","year":"2020","unstructured":"Shruti Jadon. 2020. A survey of loss functions for semantic segmentation. In 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE, 1\u20137."},{"issue":"15","key":"e_1_3_1_37_2","doi-asserted-by":"crossref","first-page":"11141","DOI":"10.1007\/s00521-023-08290-w","article-title":"An adaptive multi-class imbalanced classification framework based on ensemble methods and deep network","volume":"35","author":"Jiang Xuezheng","year":"2023","unstructured":"Xuezheng Jiang, Junyi Wang, Qinggang Meng, Mohamad Saada, and Haibin Cai. 2023. An adaptive multi-class imbalanced classification framework based on ensemble methods and deep network. Neural Computing and Applications 35, 15 (2023), 11141\u201311159.","journal-title":"Neural Computing and Applications"},{"key":"e_1_3_1_38_2","unstructured":"Kaggle.Com. 2019. APTOS : Eye Preprocessing in Diabetic Retinopathy | Kaggle. Retrieved from https:\/\/www.kaggle.com\/code\/ratthachat\/aptos-eye-preprocessing-in-diabetic-retinopathy?scriptVersionId=20340219"},{"key":"e_1_3_1_39_2","unstructured":"Kaggle.Com. 2019. APTOS 2019 Blindness Detection. Retrieved from https:\/\/kaggle.com\/competitions\/aptos2019-blindness-detection"},{"key":"e_1_3_1_40_2","first-page":"234","volume-title":"2023 IEEE Conference on Software Testing, Verification and Validation (ICST)","author":"Kim Jinhan","year":"2023","unstructured":"Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella, and Shin Yoo. 2023. Repairing DNN architecture: Are we there yet? In 2023 IEEE Conference on Software Testing, Verification and Validation (ICST). IEEE, 234\u2013245."},{"key":"e_1_3_1_41_2","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. Retrieved from https:\/\/arxiv.org\/abs\/1609.02907"},{"key":"e_1_3_1_42_2","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features From Tiny Images. Technical Report University of Toronto Toronto."},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","first-page":"46084","DOI":"10.1109\/ACCESS.2018.2866197","article-title":"Multi-targeted adversarial example in evasion attack on deep neural network","volume":"6","author":"Kwon Hyun","year":"2018","unstructured":"Hyun Kwon, Yongchul Kim, Ki-Woong Park, Hyunsoo Yoon, and Daeseon Choi. 2018. Multi-targeted adversarial example in evasion attack on deep neural network. IEEE Access 6 (2018), 46084\u201346096.","journal-title":"IEEE Access"},{"issue":"1","key":"e_1_3_1_44_2","first-page":"1533","article-title":"Understanding deep learning via decision boundary","volume":"36","author":"Lei Shiye","year":"2023","unstructured":"Shiye Lei, Fengxiang He, Yancheng Yuan, and Dacheng Tao. 2023. Understanding deep learning via decision boundary. IEEE Transactions on Neural Networks and Learning Systems 36, 1 (2023), 1533\u20131544.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"e_1_3_1_45_2","first-page":"1","article-title":"Faire: Repairing fairness of neural networks via neuron condition synthesis","volume":"33","author":"Li Tianlin","year":"2023","unstructured":"Tianlin Li, Xiaofei Xie, Jian Wang, Qing Guo, Aishan Liu, Lei Ma, and Yang Liu. 2023. Faire: Repairing fairness of neural networks via neuron condition synthesis. ACM Transactions on Software Engineering and Methodology 33, 1 (2023), 1\u201324.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"issue":"6","key":"e_1_3_1_46_2","doi-asserted-by":"crossref","first-page":"1396","DOI":"10.1109\/TSE.2024.3385538","article-title":"Test input prioritization for graph neural networks","volume":"50","author":"Li Yinghua","year":"2024","unstructured":"Yinghua Li, Xueqi Dang, Weiguo Pian, Andrew Habib, Jacques Klein, and Tegawend\u00e9 Bissyand\u00e9. 2024. Test input prioritization for graph neural networks. IEEE Transactions on Software Engineering 50, 6 (2024), 1396\u20131424.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_1_47_2","doi-asserted-by":"crossref","unstructured":"T. Lin P. Goyal R. Girshick K. He P. Doll\u00e1r. 2017. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_1_48_2","first-page":"175","volume-title":"2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","author":"Ma Shiqing","year":"2018","unstructured":"Shiqing Ma, Yingqi Liu, Wen-Chuan Lee, Xiangyu Zhang, and Ananth Grama. 2018. MODE: Automated neural network model debugging via state differential analysis and input selection. In 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 175\u2013186."},{"key":"e_1_3_1_49_2","unstructured":"Microsoft. 2024. Microsoft Security Incident Prediction. Retrieved from https:\/\/www.kaggle.com\/datasets\/Microsoft\/microsoft-security-incident-prediction\/data"},{"issue":"3","key":"e_1_3_1_50_2","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1109\/JPROC.2020.2970615","article-title":"Adversarial learning targeting deep neural network classification: A comprehensive review of defenses against attacks","volume":"108","author":"Miller David J.","year":"2020","unstructured":"David J. Miller, Zhen Xiang, and George Kesidis. 2020. Adversarial learning targeting deep neural network classification: A comprehensive review of defenses against attacks. Proceedings of the IEEE 108, 3 (2020), 402\u2013433.","journal-title":"Proceedings of the IEEE"},{"key":"e_1_3_1_51_2","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Vol. 4.","journal-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"104773","DOI":"10.1016\/j.engappai.2022.104773","article-title":"A systematic literature review on software defect prediction using artificial intelligence: Datasets, data validation methods, approaches, and tools","volume":"111","author":"Pachouly Jalaj","year":"2022","unstructured":"Jalaj Pachouly, Swati Ahirrao, Ketan Kotecha, Ganeshsree Selvachandran, and Ajith Abraham. 2022. A systematic literature review on software defect prediction using artificial intelligence: Datasets, data validation methods, approaches, and tools. Engineering Applications of Artificial Intelligence 111 (2022), 104773.","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"e_1_3_1_53_2","first-page":"889","volume-title":"28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","author":"Pan Rangeet","year":"2020","unstructured":"Rangeet Pan and Hridesh Rajan. 2020. On decomposing a deep neural network into modules. In 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 889\u2013900."},{"key":"e_1_3_1_54_2","first-page":"524","volume-title":"44th International Conference on Software Engineering","author":"Pan Rangeet","year":"2022","unstructured":"Rangeet Pan and Hridesh Rajan. 2022. Decomposing convolutional neural networks into reusable and replaceable modules. In 44th International Conference on Software Engineering, 524\u2013535."},{"issue":"1","key":"e_1_3_1_55_2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.ress.2010.06.029","article-title":"A critical view of severity classification in risk assessment methods","volume":"96","author":"Pasquini Alberto","year":"2011","unstructured":"Alberto Pasquini, Simone Pozzi, and Luca Save. 2011. A critical view of severity classification in risk assessment methods. Reliability Engineering & System Safety 96, 1 (Jan. 2011), 53\u201363. Retrieved from https:\/\/doi.org\/10.1016\/j.ress.2010.06.029","journal-title":"Reliability Engineering & System Safety"},{"key":"e_1_3_1_56_2","first-page":"1","volume-title":"37th IEEE\/ACM International Conference on Automated Software Engineering","author":"Qi Binhang","year":"2022","unstructured":"Binhang Qi, Hailong Sun, Xiang Gao, and Hongyu Zhang. 2022. Patching weak convolutional neural network models through modularization and composition. In 37th IEEE\/ACM International Conference on Automated Software Engineering, 1\u201312."},{"issue":"3","key":"e_1_3_1_57_2","first-page":"1","article-title":"Reusing convolutional neural network models through modularization and composition","volume":"33","author":"Qi Binhang","year":"2024","unstructured":"Binhang Qi, Hailong Sun, Hongyu Zhang, and Xiang Gao. 2024. Reusing convolutional neural network models through modularization and composition. ACM Transactions on Software Engineering and Methodology 33, 3 (2024), 1\u201339.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_58_2","first-page":"1","volume-title":"46th IEEE\/ACM International Conference on Software Engineering","author":"Qi Binhang","year":"2024","unstructured":"Binhang Qi, Hailong Sun, Hongyu Zhang, Ruobing Zhao, and Xiang Gao. 2024. Modularizing while training: A new paradigm for modularizing DNN models. In 46th IEEE\/ACM International Conference on Software Engineering, 1\u201312."},{"key":"e_1_3_1_59_2","unstructured":"Aditi Raghunathan Sang Michael Xie Fanny Yang John C. Duchi and Percy Liang. 2019. Adversarial training can hurt generalization. arXiv:1906.06032. Retrieved from https:\/\/arxiv.org\/abs\/1906.06032"},{"key":"e_1_3_1_60_2","first-page":"4700","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ro Yeonju","year":"2023","unstructured":"Yeonju Ro, Cong Xu, Agnieszka Ciborowska, Suparna Bhattacharya, Frankie Li, and Martin Foltin. 2023. Dataset efficient training with model ensembling. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4700\u20134704."},{"issue":"2","key":"e_1_3_1_61_2","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/TSE.2022.3163682","article-title":"Increasing the confidence of deep neural networks by coverage analysis","volume":"49","author":"Rossolini Giulio","year":"2022","unstructured":"Giulio Rossolini, Alessandro Biondi, and Giorgio Buttazzo. 2022. Increasing the confidence of deep neural networks by coverage analysis. IEEE Transactions on Software Engineering 49, 2 (2022), 802\u2013815.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_1_62_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky Olga","year":"2015","unstructured":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. 2015. Imagenet large scale visual recognition challenge. International Journal of Computer Vision 115 (2015), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_1_63_2","unstructured":"Credit score classification. 2022. Credit Score Classification. Retrieved from https:\/\/www.kaggle.com\/datasets\/parisrohan\/credit-score-classification"},{"key":"e_1_3_1_64_2","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding Machine Learning: From Theory to Algorithms","author":"Shalev-Shwartz Shai","year":"2014","unstructured":"Shai Shalev-Shwartz and Shai Ben-David. 2014. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press."},{"key":"e_1_3_1_65_2","unstructured":"Ambesh Shekhar. 2021. ImageNet100. Retrieved from https:\/\/www.kaggle.com\/datasets\/ambityga\/imagenet100\/data"},{"key":"e_1_3_1_66_2","first-page":"3145","volume-title":"34th International Conference on Machine Learning","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In 34th International Conference on Machine Learning. PMLR, 3145\u20133153. Retrieved from https:\/\/proceedings.mlr.press\/v70\/shrikumar17a.html"},{"issue":"10","key":"e_1_3_1_67_2","doi-asserted-by":"crossref","first-page":"2517","DOI":"10.1007\/s11263-022-01643-3","article-title":"Class-difficulty based methods for long-tailed visual recognition","volume":"130","author":"Sinha Saptarshi","year":"2022","unstructured":"Saptarshi Sinha, Hiroki Ohashi, and Katsuyuki Nakamura. 2022. Class-difficulty based methods for long-tailed visual recognition. International Journal of Computer Vision 130, 10 (2022), 2517\u20132531.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_1_68_2","unstructured":"sohn. 2019. Open-Source Code of Arachne. Retrieved from https:\/\/github.com\/coinse\/arachne"},{"issue":"4","key":"e_1_3_1_69_2","first-page":"85:1","article-title":"Arachne: Search-based repair of deep neural networks","volume":"32","author":"Sohn Jeongju","year":"2023","unstructured":"Jeongju Sohn, Sungmin Kang, and Shin Yoo. 2023. Arachne: Search-based repair of deep neural networks. ACM Transactions on Software Engineering and Methodology 32, 4 (May 2023), 85:1\u201385:26. Retrieved from https:\/\/doi.org\/10.1145\/3563210","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","article-title":"A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects","volume":"285","author":"Song Kechen","year":"2013","unstructured":"Kechen Song and Yunhui Yan. 2013. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Applied Surface Science 285 (2013), 858\u2013864.","journal-title":"Applied Surface Science"},{"key":"e_1_3_1_71_2","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1145\/3356250.3360025","volume-title":"17th Conference on Embedded Networked Sensor Systems","author":"Song Qun","year":"2019","unstructured":"Qun Song, Zhenyu Yan, and Rui Tan. 2019. Moving target defense for embedded deep visual sensing against adversarial examples. In 17th Conference on Embedded Networked Sensor Systems, 124\u2013137."},{"key":"e_1_3_1_72_2","unstructured":"Jost Tobias Springenberg Alexey Dosovitskiy Thomas Brox and Martin Riedmiller. 2014. Striving for simplicity: The all convolutional net. arXiv:1412.6806. Retrieved from https:\/\/arxiv.org\/abs\/1412.6806"},{"issue":"1","key":"e_1_3_1_73_2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 1929\u20131958.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_1_74_2","first-page":"338","volume-title":"44th International Conference on Software Engineering","author":"Sun Bing","year":"2022","unstructured":"Bing Sun, Jun Sun, Long H. Pham, and Jie Shi. 2022. Causality-based neural network repair. In 44th International Conference on Software Engineering, 338\u2013349."},{"key":"e_1_3_1_75_2","unstructured":"Ruoyu Sun. 2019. Optimization for deep learning: Theory and algorithms. arXiv:1912.08957. Retrieved from https:\/\/arxiv.org\/abs\/1912.08957"},{"key":"e_1_3_1_76_2","doi-asserted-by":"crossref","unstructured":"Ye Tian and Yang Feng. 2021. Neyman-pearson multi-class classification via cost-sensitive learning. arXiv:2111.04597. Retrieved from https:\/\/arxiv.org\/abs\/2111.04597","DOI":"10.32614\/CRAN.package.npcs"},{"key":"e_1_3_1_77_2","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1109\/SANER53432.2022.00128","volume-title":"2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","author":"Tokui Shogo","year":"2022","unstructured":"Shogo Tokui, Susumu Tokumoto, Akihito Yoshii, Fuyuki Ishikawa, Takao Nakagawa, Kazuki Munakata, and Shinji Kikuchi. 2022. Neurecover: Regression-controlled repair of deep neural networks with training history. In 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE, 1111\u20131121."},{"issue":"9","key":"e_1_3_1_78_2","first-page":"1886","article-title":"Kernel spectral embedding transfer ensemble for heterogeneous defect prediction","volume":"47","author":"Tong Haonan","year":"2019","unstructured":"Haonan Tong, Bin Liu, and Shihai Wang. 2019. Kernel spectral embedding transfer ensemble for heterogeneous defect prediction. IEEE Transactions on Software Engineering 47, 9 (2019), 1886\u20131906.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_1_79_2","unstructured":"Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner and Aleksander Madry. 2018. Robustness may be at odds with accuracy. arXiv:1805.12152. Retrieved from https:\/\/arxiv.org\/abs\/1805.12152"},{"key":"e_1_3_1_80_2","first-page":"5785","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Kumar Pavan","year":"2023","unstructured":"Pavan Kumar, Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. 2023. Fastvit: A fast hybrid vision transformer using structural reparameterization. In IEEE\/CVF International Conference on Computer Vision, 5785\u20135795."},{"key":"e_1_3_1_81_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_82_2","first-page":"3784","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang Jianfeng","year":"2021","unstructured":"Jianfeng Wang, Thomas Lukasiewicz, Xiaolin Hu, Jianfei Cai, and Zhenghua Xu. 2021. Rsg: A simple but effective module for learning imbalanced datasets. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3784\u20133793."},{"key":"e_1_3_1_83_2","first-page":"561","volume-title":"44th International Conference on Software Engineering","author":"Wardat Mohammad","year":"2022","unstructured":"Mohammad Wardat, Breno Dantas Cruz, Wei Le, and Hridesh Rajan. 2022. Deepdiagnosis: Automatically diagnosing faults and recommending actionable fixes in deep learning programs. In 44th International Conference on Software Engineering, 561\u2013572."},{"key":"e_1_3_1_84_2","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/ICSE43902.2021.00034","volume-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","author":"Wardat Mohammad","year":"2021","unstructured":"Mohammad Wardat, Wei Le, and Hridesh Rajan. 2021. Deeplocalize: Fault localization for deep neural networks. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, 251\u2013262."},{"issue":"6","key":"e_1_3_1_85_2","first-page":"1","article-title":"DeepPatch: Maintaining deep learning model programs to retain standard accuracy with substantial robustness improvement","volume":"32","author":"Wei Zhengyuan","year":"2023","unstructured":"Zhengyuan Wei, Haipeng Wang, Imran Ashraf, and Wing-Kwong Chan. 2023. DeepPatch: Maintaining deep learning model programs to retain standard accuracy with substantial robustness improvement. ACM Transactions on Software Engineering and Methodology 32, 6 (Jun. 2023), 1\u201349. DOI: https:\/\/doi.org\/10.1145\/3604609","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_86_2","first-page":"1","volume-title":"2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","author":"Wong Sebastien C.","year":"2016","unstructured":"Sebastien C. Wong, Adam Gatt, Victor Stamatescu, and Mark D. McDonnell. 2016. Understanding data augmentation for classification: When to warp? In 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA). IEEE, 1\u20136."},{"key":"e_1_3_1_87_2","first-page":"162","volume-title":"16th European Conference on Computer Vision (ECCV \u201920)","author":"Wu Tong","year":"2020","unstructured":"Tong Wu, Qingqiu Huang, Ziwei Liu, Yu Wang, and Dahua Lin. 2020. Distribution-balanced loss for multi-label classification in long-tailed datasets. In 16th European Conference on Computer Vision (ECCV \u201920). Springer, 162\u2013178."},{"key":"e_1_3_1_88_2","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747. Retrieved from https:\/\/arxiv.org\/abs\/1708.07747"},{"key":"e_1_3_1_89_2","first-page":"1","volume-title":"2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT)","author":"Xu Chuanyun","year":"2022","unstructured":"Chuanyun Xu, Yu Zheng, Yang Zhang, Chengjie Sun, Gang Li, and Zhaohan Zhu. 2022. Adaptive class-balanced loss based on re-weighting. In 2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT). IEEE, 1\u20138."},{"key":"e_1_3_1_90_2","first-page":"8588","article-title":"A closer look at accuracy vs. robustness","volume":"33","author":"Yang Yao-Yuan","year":"2020","unstructured":"Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Russ R. Salakhutdinov, and Kamalika Chaudhuri. 2020. A closer look at accuracy vs. robustness. In Advances in Neural Information Processing Systems, Vol. 33, 8588\u20138601.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_91_2","first-page":"40","volume-title":"International Conference on Machine Learning","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William Cohen, and Ruslan Salakhudinov. 2016. Revisiting semi-supervised learning with graph embeddings. In International Conference on Machine Learning. PMLR, 40\u201348."},{"key":"e_1_3_1_92_2","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/ISIMP.2004.1434171","volume-title":"Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004","author":"Yi-de Ma","year":"2004","unstructured":"Ma Yi-de, Liu Qing, and Qian Zhi-Bai. 2004. Automated image segmentation using improved PCNN model based on cross-entropy. In Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. IEEE, 743\u2013746."},{"issue":"1","key":"e_1_3_1_93_2","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s10845-022-02053-5","article-title":"A novel automatic classification approach for micro-flaws on the large-aperture optics surface based on multi-light source fusion and integrated deep learning architecture","volume":"35","author":"Yin Zhaoyang","year":"2024","unstructured":"Zhaoyang Yin, Mingjun Chen, Linjie Zhao, Jian Cheng, Chao Tan, Xiaotao Li, Zhiyu Lin, and Yankang Chen. 2024. A novel automatic classification approach for micro-flaws on the large-aperture optics surface based on multi-light source fusion and integrated deep learning architecture. Journal of Intelligent Manufacturing 35, 1 (2024), 413\u2013428.","journal-title":"Journal of Intelligent Manufacturing"},{"issue":"6","key":"e_1_3_1_94_2","first-page":"1","article-title":"Mitigating regression faults induced by feature evolution in deep learning systems","volume":"34","author":"You Hanmo","year":"2025","unstructured":"Hanmo You, Zan Wang, Xuyang Chen, Junjie Chen, Jun Sun, Shuang Liu, and Zishuo Dong. 2025. Mitigating regression faults induced by feature evolution in deep learning systems. ACM Transactions on Software Engineering and Methodology 34, 6 (2025), 1\u201333.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_1_95_2","first-page":"157","article-title":"Feature representation learning in deep neural networks","author":"Yu Dong","year":"2015","unstructured":"Dong Yu, Li Deng, Dong Yu, and Li Deng. 2015. Feature representation learning in deep neural networks. In Automatic Speech Recognition: A Deep Learning Approach. Springer, 157\u2013175.","journal-title":"Automatic Speech Recognition: A Deep Learning Approach"},{"key":"e_1_3_1_96_2","first-page":"70","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yu Sihao","year":"2022","unstructured":"Sihao Yu, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Zizhen Wang, and Xueqi Cheng. 2022. A re-balancing strategy for class-imbalanced classification based on instance difficulty. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 70\u201379. DOI: 10.1109\/CVPR52688.2022.00017Conference"},{"key":"e_1_3_1_97_2","first-page":"818","volume-title":"13th European Conference on Computer Vision (ECCV \u201914)","author":"Zeiler Matthew D.","year":"2014","unstructured":"Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In 13th European Conference on Computer Vision (ECCV \u201914). Springer, 818\u2013833."},{"key":"e_1_3_1_98_2","unstructured":"Ruslan Zhabskyi. 2024. Security Incident Prediction. Retrieved from https:\/\/www.kaggle.com\/code\/ruslanzhabskyi\/security-incident-prediction"},{"key":"e_1_3_1_99_2","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/ASE.2019.00043","volume-title":"2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Zhang Hao","year":"2019","unstructured":"Hao Zhang and W. K. Chan. 2019. Apricot: A weight-adaptation approach to fixing deep learning models. In 2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE), 376\u2013387. DOI: 10.1109\/ASE.2019.00043"},{"key":"e_1_3_1_100_2","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1109\/ICSE43902.2021.00043","volume-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","author":"Zhang Xiaoyu","year":"2021","unstructured":"Xiaoyu Zhang, Juan Zhai, Shiqing Ma, and Chao Shen. 2021. Autotrainer: An automatic dnn training problem detection and repair system. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, 359\u2013371."},{"key":"e_1_3_1_101_2","first-page":"141","volume-title":"2021 ACM SIGSAC Conference on Computer and Communications Security","author":"Zhao Yue","year":"2021","unstructured":"Yue Zhao, Hong Zhu, Kai Chen, and Shengzhi Zhang. 2021. AI-Lancet: Locating error-inducing neurons to optimize neural networks. In 2021 ACM SIGSAC Conference on Computer and Communications Security. ACM, 141\u2013158. DOI: 10.1145\/3460120.3484818"},{"key":"e_1_3_1_102_2","first-page":"4424","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Zhu Kaijie","year":"2023","unstructured":"Kaijie Zhu, Xixu Hu, Jindong Wang, Xing Xie, and Ge Yang. 2023. Improving generalization of adversarial training via robust critical fine-tuning. In IEEE\/CVF International Conference on Computer Vision, 4424\u20134434."}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3771545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:42:11Z","timestamp":1783694531000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3771545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":101,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3771545"],"URL":"https:\/\/doi.org\/10.1145\/3771545","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"2024-10-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}