{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:38:12Z","timestamp":1769729892173,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":87,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["(No. 62102284, 61872262)"],"award-info":[{"award-number":["(No. 62102284, 61872262)"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Ministry of Education, Singapore under its Academic Research Fund Tier 1","award":["21-SIS-SMU-033"],"award-info":[{"award-number":["21-SIS-SMU-033"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3551349.3560427","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T20:43:54Z","timestamp":1672951434000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Towards Understanding the Faults of JavaScript-Based Deep Learning Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0405-835X","authenticated-orcid":false,"given":"Lili","family":"Quan","sequence":"first","affiliation":[{"name":"Tianjin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-4100","authenticated-orcid":false,"given":"Qianyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, China"}]},{"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"given":"Sen","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University, China"}]},{"given":"Xiaohong","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University, China"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2023,1,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. Keras: The Python Deep Learning Library. https:\/\/keras.io"},{"key":"e_1_3_2_1_2_1","unstructured":"2022. ML5.js. https:\/\/learn.ml5js.org"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. Website of this study. https:\/\/sites.google.com\/view\/dl-fault-study4js"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI. USENIX Association, 265\u2013283","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0Gordon Murray, Benoit Steiner, Paul\u00a0A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI. USENIX Association, 265\u2013283."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901739.2903506"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2827384"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations, ICLR. OpenReview.net.","author":"Brendel Wieland","year":"2018","unstructured":"Wieland Brendel, Jonas Rauber, and Matthias Bethge. 2018. Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models. In Proceedings of the 6th International Conference on Learning Representations, ICLR. OpenReview.net."},{"key":"e_1_3_2_1_8_1","unstructured":"Junming Cao Bihuan Chen Chao Sun Longjie Hu and Xin Peng. 2021. Characterizing Performance Bugs in Deep Learning Systems. arXiv preprint arXiv:2112.01771(2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"e_1_3_2_1_11_1","unstructured":"Guangke Chen Zhe Zhao Fu Song Sen Chen Lingling Fan and Yang Liu. 2022. AS2T: Arbitrary source-to-target adversarial attack on speaker recognition systems. arXiv preprint arXiv:2206.03351(2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978394"},{"key":"e_1_3_2_1_13_1","unstructured":"Junjie Chen Yihua Liang Qingchao Shen and Jiajun Jiang. 2022. Toward Understanding Deep Learning Framework Bugs. arXiv preprint arXiv:2203.04026(2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Sen Chen Minhui Xue Lingling Fan Shuang Hao Lihua Xu Haojin Zhu and Bo Li. 2018. Automated poisoning attacks and defenses in malware detection systems: An adversarial machine learning approach. computers & security 73(2018) 326\u2013344.","DOI":"10.1016\/j.cose.2017.11.007"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409759"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00068"},{"key":"e_1_3_2_1_17_1","volume-title":"A coefficient of agreement for nominal scales. Educational and psychological measurement 20, 1","author":"Cohen Jacob","year":"1960","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20, 1 (1960), 37\u201346."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.3000681"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00010"},{"key":"e_1_3_2_1_20_1","unstructured":"Github. 2022. About Stars. https:\/\/help.github.com\/articles\/about-stars\/"},{"key":"e_1_3_2_1_21_1","unstructured":"Github. 2022. Forking a Repo. https:\/\/help.github.com\/articles\/fork-a-repo\/"},{"key":"e_1_3_2_1_22_1","unstructured":"Github. 2022. Github Serach API. https:\/\/docs.github.com\/cn\/rest\/search"},{"key":"e_1_3_2_1_23_1","unstructured":"Github. 2022. Issues. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5486"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations, ICLR.","author":"Goodfellow J.","year":"2015","unstructured":"Ian\u00a0J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In Proceedings of the 3rd International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations, ICLR.","author":"Goodfellow J.","year":"2015","unstructured":"Ian\u00a0J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In Proceedings of the 3rd International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_26_1","unstructured":"google. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/299"},{"key":"e_1_3_2_1_27_1","unstructured":"google. 2022. face-api.js. https:\/\/github.com\/PaddlePaddle\/Paddle.js"},{"key":"e_1_3_2_1_28_1","unstructured":"google. 2022. face-api.js. https:\/\/github.com\/mil-tokyo\/webdnn"},{"key":"e_1_3_2_1_29_1","unstructured":"Google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs"},{"key":"e_1_3_2_1_30_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/4768"},{"key":"e_1_3_2_1_31_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/4593"},{"key":"e_1_3_2_1_32_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5800"},{"key":"e_1_3_2_1_33_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5641"},{"key":"e_1_3_2_1_34_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/4378"},{"key":"e_1_3_2_1_35_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5334"},{"key":"e_1_3_2_1_36_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5110"},{"key":"e_1_3_2_1_37_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5700"},{"key":"e_1_3_2_1_38_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/4745"},{"key":"e_1_3_2_1_39_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5492"},{"key":"e_1_3_2_1_40_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5702"},{"key":"e_1_3_2_1_41_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5454"},{"key":"e_1_3_2_1_42_1","unstructured":"google. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/4852"},{"key":"e_1_3_2_1_43_1","unstructured":"google. 2022. XNNPACK. https:\/\/github.com\/google\/XNNPACK"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_45_1","unstructured":"Diandian Gu Zhenpeng Chen Yuanqiang Liu Zili Zhang Yun Ma Xin Jin and Xuanzhe Liu. 2021. Demystifying Developers\u2019 Issues in Distributed Training of Deep Learning Software. arXiv preprint arXiv:2112.06222(2021)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00080"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416571"},{"key":"e_1_3_2_1_48_1","unstructured":"Hannes Hapke and Catherine Nelson. 2020. Building Machine Learning Pipelines. O\u2019Reilly Media."},{"key":"e_1_3_2_1_49_1","unstructured":"Nima\u00a0Shiri Harzevili Jiho Shin Junjie Wang and Song Wang. 2022. Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries. arXiv preprint arXiv:2203.06502(2022)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380395"},{"key":"e_1_3_2_1_52_1","unstructured":"infinitered. 2022. nsfwjs. https:\/\/github.com\/infinitered\/nsfwjs\/issues\/16"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338955"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380378"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59410-7_40"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.110935"},{"key":"e_1_3_2_1_57_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/788"},{"key":"e_1_3_2_1_58_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/826"},{"key":"e_1_3_2_1_59_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/59"},{"key":"e_1_3_2_1_60_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/66"},{"key":"e_1_3_2_1_61_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/794"},{"key":"e_1_3_2_1_62_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/32"},{"key":"e_1_3_2_1_63_1","unstructured":"justadudewhohacks. 2022. face-api.js. https:\/\/github.com\/justadudewhohacks\/face-api.js\/issues\/77"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2014.6868045"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2018.00021"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313639"},{"key":"e_1_3_2_1_67_1","unstructured":"Microsoft. 2022. TypeScript. https:\/\/www.typescriptlang.org\/"},{"key":"e_1_3_2_1_68_1","unstructured":"Mozilla. 2022. Fetch API. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Fetch_API"},{"key":"e_1_3_2_1_69_1","unstructured":"Mozilla. 2022. Same-origin policy. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/Security\/Same-origin_policy"},{"key":"e_1_3_2_1_70_1","unstructured":"nsfwjs. 2022. nsfwjs. https:\/\/github.com\/infinitered\/nsfwjs\/issues\/461"},{"key":"e_1_3_2_1_71_1","unstructured":"Nicolas Papernot Patrick\u00a0D. McDaniel Ian\u00a0J. Goodfellow Somesh Jha Z.\u00a0Berkay Celik and Ananthram Swami. 2016. Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples. CoRR abs\/1602.02697(2016). arXiv:1602.02697http:\/\/arxiv.org\/abs\/1602.02697"},{"key":"e_1_3_2_1_72_1","volume-title":"Automatic Differentiation in PyTorch. Openreview","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. Openreview (2017)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00107"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/32.799955"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC.2017.41"},{"key":"e_1_3_2_1_76_1","unstructured":"Florian Tambon Amin Nikanjam Le An Foutse Khomh and Giuliano Antoniol. 2021. Silent Bugs in Deep Learning Frameworks: An Empirical Study of Keras and TensorFlow. arXiv preprint arXiv:2112.13314(2021)."},{"key":"e_1_3_2_1_77_1","unstructured":"TensorFlow.js. 2022. Issues. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5821"},{"key":"e_1_3_2_1_78_1","unstructured":"TensorFlow.js. 2022. Issues. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5632"},{"key":"e_1_3_2_1_79_1","unstructured":"TensorFlow.js. 2022. TensorFlow.js. https:\/\/github.com\/tensorflow\/tfjs\/issues\/5246"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2012.22"},{"key":"e_1_3_2_1_81_1","unstructured":"Transcranial. 2022. Keras.js. https:\/\/github.com\/transcranial\/keras-js"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409761"},{"key":"e_1_3_2_1_83_1","unstructured":"Wikipedia. 2022. Document Object Model. https:\/\/en.wikipedia.org\/wiki\/Document_Object_Model"},{"key":"e_1_3_2_1_84_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc\u00a0V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Greg Corrado Macduff Hughes and Jeffrey Dean. 2016. Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR abs\/1609.08144(2016). arXiv:1609.08144http:\/\/arxiv.org\/abs\/1609.08144"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00027"},{"key":"e_1_3_2_1_86_1","volume-title":"AUTOTRAINER: An Automatic DNN Training Problem Detection and Repair System. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, 359\u2013371","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_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213866"}],"event":{"name":"ASE '22: 37th IEEE\/ACM International Conference on Automated Software Engineering","location":"Rochester MI USA","acronym":"ASE '22"},"container-title":["Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551349.3560427","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3551349.3560427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:58:50Z","timestamp":1755849530000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551349.3560427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":87,"alternative-id":["10.1145\/3551349.3560427","10.1145\/3551349"],"URL":"https:\/\/doi.org\/10.1145\/3551349.3560427","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2023-01-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}