{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T05:24:01Z","timestamp":1775453041758,"version":"3.50.1"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tdsc.2024.3367737","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T19:05:08Z","timestamp":1708455908000},"page":"4997-5013","source":"Crossref","is-referenced-by-count":18,"title":["The \u201cCode\u201d of Ethics: A Holistic Audit of AI Code Generators"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6305-1740","authenticated-orcid":false,"given":"Wanlun","family":"Ma","sequence":"first","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-2695","authenticated-orcid":false,"given":"Yiliao","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer and Mathematical Sciences, University of Adelaide, Adelaide, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9172-4252","authenticated-orcid":false,"given":"Minhui","family":"Xue","sequence":"additional","affiliation":[{"name":"Cybersecurity and Quantum Systems Group, CSIRO's Data61, Eveleigh, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0655-666X","authenticated-orcid":false,"given":"Sheng","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-0831","authenticated-orcid":false,"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"}]}],"member":"263","reference":[{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00083"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243738"},{"key":"ref7","article-title":"CM3: A causal masked multimodal model of the internet","author":"Aghajanyan","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.35179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3290353"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.804"},{"key":"ref12","article-title":"Multi-lingual evaluation of code generation models","author":"Athiwaratkun","year":"2022"},{"key":"ref13","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref14","first-page":"932","article-title":"A neural probabilistic language model","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557079"},{"key":"ref16","article-title":"GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow (v1.1.1). Zenodo.","author":"Black","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3511265.3550449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468606"},{"key":"ref19","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-2895792\/v1","article-title":"A categorical archive of ChatGPT failures","author":"Borji","year":"2023"},{"key":"ref21","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref22","first-page":"255","article-title":"De-anonymizing programmers via code stylometry","volume-title":"Proc. 24th USENIX Secur. Symp.","author":"Caliskan-Islam"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"ref24","article-title":"A pathway towards responsible AI generated content","author":"Chen","year":"2023"},{"key":"ref25","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.728"},{"key":"ref27","article-title":"DocSparse on twitter","author":"Davis","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.436"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2007.12.013"},{"key":"ref32","first-page":"1","article-title":"InCoder: A generative model for code infilling and synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fried"},{"key":"ref33","article-title":"The Pile: An 800GB dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3019"},{"key":"ref35","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"ref37","article-title":"MGTBench: Benchmarking machine-generated text detection","author":"He","year":"2023"},{"key":"ref38","article-title":"Openais hunger for data is coming back to bite it","author":"Heikkil\u00e4","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4404340"},{"key":"ref40","first-page":"1","article-title":"Measuring coding challenge competence with apps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hendrycks"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00299"},{"key":"ref42","article-title":"GitHub on BigQuery: Analyze all the open source code","author":"Hoffa","year":"2016"},{"key":"ref43","first-page":"1","article-title":"The curious case of neural text degeneration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Holtzman"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3523273"},{"key":"ref45","article-title":"Perplexity of fixed-length models","year":"2022"},{"key":"ref46","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.164"},{"key":"ref48","article-title":"Membership inference attack susceptibility of clinical language models","author":"Jagannatha","year":"2021"},{"key":"ref49","first-page":"5110","article-title":"Learning and evaluating contextual embedding of source code","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kanade"},{"key":"ref50","article-title":"Captum: A unified and generic model interpretability library for pytorch","author":"Kokhlikyan","year":"2020"},{"key":"ref51","first-page":"21314","article-title":"CodeRL: Mastering code generation through pretrained models and deep reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Le"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510181"},{"key":"ref55","article-title":"Learning deep kernels for non-parametric two-sample tests","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref56","first-page":"829","article-title":"Statistical model criticism using kernel two sample tests","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lloyd"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref58","first-page":"1","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref59","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning","year":"1999"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.570"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.119"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.155"},{"key":"ref63","first-page":"2287","article-title":"Quantifying the privacy risks of learning high-dimensional graphical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Murakonda"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1098\/rsta.1933.0009","article-title":"On the problem of the most efficient tests of statistical hypotheses","volume":"231","author":"Neyman","year":"1933","journal-title":"Philos. Trans. Roy. Soc. London"},{"key":"ref65","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022"},{"key":"ref66","article-title":"ChatGPT: Optimizing language models for dialogue?","year":"2022"},{"key":"ref67","article-title":"Temporary policy: ChatGPT is banned","author":"Overflow","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00095"},{"issue":"8","key":"ref69","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019"},{"key":"ref70","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3022671.2984041"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.88"},{"key":"ref73","article-title":"Mitsuhiko on twitter","author":"Ronacher","year":"2021"},{"key":"ref74","first-page":"8326","article-title":"Radioactive data: Tracing through training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sablayrolles"},{"key":"ref75","first-page":"535","article-title":"Saving softwares fair use future","volume":"31","author":"Samuelson","year":"2017","journal-title":"Harv. JL & Tech."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872770"},{"key":"ref77","first-page":"582","article-title":"Support vector method for novelty detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sch\u00f6lkopf"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref79","first-page":"1","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Serr\u00e0"},{"key":"ref80","article-title":"In ChatGPT we trust? Measuring and characterizing the reliability of ChatGPT","author":"Shen","year":"2023"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330885"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512225"},{"key":"ref84","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref85","first-page":"1","article-title":"Generative models and model criticism via optimized maximum mean discrepancy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutherland"},{"key":"ref86","volume-title":"Natural Language Processing With Transformers","author":"Tunstall","year":"2022"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.673"},{"key":"ref88","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref89","article-title":"GPT-J-6B: A 6 billion parameter autoregressive language model","author":"Wang","year":"2021"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref91","first-page":"11","article-title":"Further analysis of outlier detection with deep generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21415"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560675"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/329"},{"key":"ref97","article-title":"Defending against neural fake news","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref98","article-title":"One small step for generative AI, one giant leap for AGI: A complete survey on ChatGPT in AIGC era","author":"Zhang","year":"2023"},{"key":"ref99","first-page":"12427","article-title":"Understanding failures in out-of-distribution detection with deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8858\/10663874\/10440501.pdf?arnumber=10440501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:05:41Z","timestamp":1725483941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":95,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2024.3367737","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}