{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T16:24:33Z","timestamp":1775924673494,"version":"3.50.1"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T00:00:00Z","timestamp":1649462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Research Foundation, Singapore under its the AI Singapore Programme","award":["AISG2-RP-2020-019"],"award-info":[{"award-number":["AISG2-RP-2020-019"]}]},{"name":"National Research Foundation, Prime Minister\u2019s Office, Singapore under its National Cybersecurity R&D Program","award":["NRF2018NCR-NCR005-0001"],"award-info":[{"award-number":["NRF2018NCR-NCR005-0001"]}]},{"name":"NRF Investigatorship","award":["NRFI06-2020-0022-0001"],"award-info":[{"award-number":["NRFI06-2020-0022-0001"]}]},{"name":"National Research Foundation through its National Satellite of Excellence in Trustworthy Software Systems (NSOE-TSS) project under the National Cybersecurity R&D","award":["NRF2018NCR-NSOE003-0001"],"award-info":[{"award-number":["NRF2018NCR-NSOE003-0001"]}]},{"name":"National Research Foundation, Singapore under its AI Singapore Programme","award":["AISG-PhD\/2021-01-022[T]"],"award-info":[{"award-number":["AISG-PhD\/2021-01-022[T]"]}]},{"name":"Ministry of Education, Singapore under its Academic Research Fund Tier 3","award":["MOET32020-0004"],"award-info":[{"award-number":["MOET32020-0004"]}]},{"name":"JSPS KAKENHI","award":["JP20H04168, JP19K24348, JP19H04086, JP21H04877"],"award-info":[{"award-number":["JP20H04168, JP19K24348, JP19H04086, JP21H04877"]}]},{"DOI":"10.13039\/501100020959","name":"JST-Mirai Program","doi-asserted-by":"crossref","award":["JPMJMI20B8"],"award-info":[{"award-number":["JPMJMI20B8"]}],"id":[{"id":"10.13039\/501100020959","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Canada CIFAR AI Program and Natural Sciences and Engineering Research Council of Canada"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2022,7,31]]},"abstract":"<jats:p>Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural Networks (DNNs) still raises concerns in the practical operational environment, which calls for systematic testing, especially in safety-critical scenarios. Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs. However, due to the blackbox nature of DNN, the existing structural coverage criteria are difficult to interpret, making it hard to understand the underlying principles of these criteria. The relationship between the structural coverage and the decision logic of DNNs is unknown. Moreover, recent studies have further revealed the non-existence of correlation between the structural coverage and DNN defect detection, which further posts concerns on what a suitable DNN testing criterion should be.<\/jats:p>\n          <jats:p>\n            In this article, we propose the\n            <jats:italic>interpretable<\/jats:italic>\n            coverage criteria through constructing the decision structure of a DNN. Mirroring the control flow graph of the traditional program, we first extract a decision graph from a DNN based on its interpretation, where a path of the decision graph represents a decision logic of the DNN. Based on the control flow and data flow of the decision graph, we propose two variants of path coverage to measure the adequacy of the test cases in exercising the decision logic. The higher the path coverage, the more diverse decision logic the DNN is expected to be explored. Our large-scale evaluation results demonstrate that: The path in the decision graph is effective in characterizing the decision of the DNN, and the proposed coverage criteria are also sensitive with errors, including natural errors and adversarial examples, and strongly correlate with the output impartiality.\n          <\/jats:p>","DOI":"10.1145\/3490489","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T17:38:58Z","timestamp":1643650738000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["NPC:\n            <u>N<\/u>\n            euron\n            <u>P<\/u>\n            ath\n            <u>C<\/u>\n            overage via Characterizing Decision Logic of Deep Neural Networks"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-6502","authenticated-orcid":false,"given":"Xiaofei","family":"Xie","sequence":"first","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"given":"Tianlin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"Kyushu University, Japan"}]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0857-8611","authenticated-orcid":false,"given":"Felix","family":"Juefei-Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Sunnyvale, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Zhejiang Sci-Tech University, China"}]}],"member":"320","published-online":{"date-parts":[[2022,4,9]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338937"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2610413"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_5_2","volume-title":"AI \u201cOutperforms\u201d Doctors Diagnosing Breast Cancer","year":"2020","unstructured":"BBC. 2020. AI \u201cOutperforms\u201d Doctors Diagnosing Breast Cancer. Retrieved from https:\/\/www.bbc.com\/news\/health-50857759."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995975"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3108009"},{"key":"e_1_3_2_10_2","unstructured":"Datamonsters. 2017. 10 Applications of Artificial Neural Networks in Natural Language Processing. Retrieved from https:\/\/medium.com\/@datamonsters\/artificial-neural-networks-in-natural-language-processing-bcf62aa9151a."},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Yizhen Dong Peixin Zhang Jingyi Wang Shuang Liu Jun Sun Jianye Hao Xinyu Wang Li Wang Jin Song Dong and Dai Ting. 2019. There Is Limited Correlation between Coverage and Robustness for Deep Neural Networks. arxiv:1911.05904 [cs.LG]","DOI":"10.1109\/ICECCS51672.2020.00016"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338954"},{"key":"e_1_3_2_13_2","unstructured":"Carnegie Endowment. 2019. The Global Expansion of AI Surveillance. Retrieved from https:\/\/carnegieendowment.org\/2019\/09\/17\/global-expansion-of-ai-surveillance-pub-79847."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397357"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377812.3390793"},{"key":"e_1_3_2_17_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Goodfellow Ian","year":"2015","unstructured":"Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of the International Conference on Learning Representations. Retrieved from http:\/\/arxiv.org\/abs\/1412.6572."},{"key":"e_1_3_2_18_2","article-title":"Watch out! Motion is blurring the vision of your deep neural networks","volume":"33","author":"Guo Qing","year":"2020","unstructured":"Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, and Yang Liu. 2020. Watch out! Motion is blurring the vision of your deep neural networks. NeurPIS 33 (2020).","journal-title":"NeurPIS"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_13"},{"key":"e_1_3_2_20_2","first-page":"11884","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Gupta Rahul","year":"2019","unstructured":"Rahul Gupta, Aditya Kanade, and Shirish Shevade. 2019. Neural attribution for semantic bug-localization in student programs. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 11884\u201311894."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409754"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.30"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3155562.3155583"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00108"},{"key":"e_1_3_2_25_2","article-title":"The Cifar-10 Dataset","author":"Krizhevsky Nair","year":"2014","unstructured":"Nair Krizhevsky, Hinton Vinod, Christopher Geoffrey, Mike Papadakis, and Anthony Ventresque. 2014. The Cifar-10 Dataset. Retrieved from http:\/\/www.cs.toronto.edu\/kriz\/cifar.html.","journal-title":"R"},{"key":"e_1_3_2_26_2","article-title":"Adversarial examples in the physical world","author":"Kurakin Alexey","year":"2016","unstructured":"Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2016. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016).","journal-title":"arXiv preprint arXiv:1607.02533"},{"key":"e_1_3_2_27_2","article-title":"The MNIST Database of Handwritten Digits","author":"LeCun Yann","year":"1998","unstructured":"Yann LeCun and Corrina Cortes. 1998. The MNIST Database of Handwritten Digits. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/.","journal-title":"R"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.08.043"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-NIER.2019.00031"},{"key":"e_1_3_2_30_2","volume-title":"Proceedings of the 30th USENIX Security Symposium (USENIX Security\u201921)","author":"Lin Yun","year":"2021","unstructured":"Yun Lin, Ruofan Liu, Dinil Mon Divakaran, Jun Yang Ng, Qing Zhou Chan, Yiwen Lu, Yuxuan Si, Fan Zhang, and Jin Song Dong. 2021. Phishpedia: A hybrid deep learning based approach to visually identify phishing webpages. In Proceedings of the 30th USENIX Security Symposium (USENIX Security\u201921)."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2019.8668044"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2018.00021"},{"key":"e_1_3_2_34_2","unstructured":"Wei Ma Mike Papadakis Anestis Tsakmalis Maxime Cordy and Yves Le Traon. 2019. Test Selection for Deep Learning Systems. arxiv:1904.13195 [cs.LG]"},{"key":"e_1_3_2_35_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_36_2","first-page":"2574","article-title":"DeepFool: A simple and accurate method to fool deep neural networks","author":"Moosavi-Dezfooli Seyed-Mohsen","year":"2016","unstructured":"Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard. 2016. DeepFool: A simple and accurate method to fool deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916). 2574\u20132582.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916)"},{"key":"e_1_3_2_37_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, Bo Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning.","journal-title":"Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"e_1_3_2_38_2","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Odena Augustus","year":"2019","unstructured":"Augustus Odena and Ian Goodfellow. 2019. TensorFuzz: Debugging neural networks with coverage-guided fuzzing. In Proceedings of the 36th International Conference on Machine Learning."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-NIER.2019.00030"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238172"},{"key":"e_1_3_2_45_2","unstructured":"TechCrunch. 2020. Nearly 70% of US Smart Speaker Owners Use Amazon Echo Devices. Retrieved from https:\/\/techcrunch.com\/2020\/02\/10\/nearly-70-of-u-s-smart-speaker-owners-use-amazon-echo-devices\/."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/145"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"e_1_3_2_48_2","unstructured":"Uber Accident. 2018. After Fatal Uber Crash a Self-Driving Start-Up Moves Forward. Retrieved from https:\/\/www.nytimes.com\/2018\/05\/07\/technology\/uber-crash-autonomous-driveai.html."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/AITest.2019.00013"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00928"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00044"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330579"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409671"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042083"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2962027"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380368"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/267580.267590"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490489","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490489","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:00Z","timestamp":1750186980000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490489"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,9]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7,31]]}},"alternative-id":["10.1145\/3490489"],"URL":"https:\/\/doi.org\/10.1145\/3490489","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,9]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}