{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:37:09Z","timestamp":1772908629391,"version":"3.50.1"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation","doi-asserted-by":"publisher","award":["NRF-NRFI08-2022-0002"],"award-info":[{"award-number":["NRF-NRFI08-2022-0002"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tse.2024.3482719","type":"journal-article","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:23:45Z","timestamp":1729877025000},"page":"3290-3306","source":"Crossref","is-referenced-by-count":13,"title":["Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models"],"prefix":"10.1109","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5938-1918","authenticated-orcid":false,"given":"Zhou","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-0286","authenticated-orcid":false,"given":"Zhipeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2436-5899","authenticated-orcid":false,"given":"Chenyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0799-5018","authenticated-orcid":false,"given":"Jieke","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0272-6860","authenticated-orcid":false,"given":"Dongsun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8599-2197","authenticated-orcid":false,"given":"DongGyun","family":"Han","sequence":"additional","affiliation":[{"name":"Royal Holloway, University of London, Egham, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4367-7201","authenticated-orcid":false,"given":"David","family":"Lo","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technol.","volume":"1","author":"Devlin","year":"2019"},{"key":"ref2","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"issue":"140","key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"J. Mach. Learn. Res.","volume":"21","author":"Raffel","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"ref5","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021"},{"key":"ref6","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3695988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510172"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/saner53432.2022.00054"},{"key":"ref10","volume-title":"Answer Summarization for Technical Queries: Benchmark and New Approach","author":"Yang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00034"},{"key":"ref12","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510146"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3428230"},{"key":"ref15","first-page":"209","article-title":"Generating adversarial computer programs using optimized obfuscations","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","volume":"16","author":"Srikant","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00070"},{"key":"ref17","article-title":"Adversarial attacks on code models with discriminative graph patterns","author":"Nguyen","year":"2023","journal-title":"CoRR"},{"key":"ref18","first-page":"1559","article-title":"You autocomplete me: Poisoning vulnerabilities in neural code completion","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur. 21)","author":"Schuster","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549153"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678946"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639074"},{"key":"ref22","first-page":"2133","article-title":"CodexLeaks: Privacy leaks from code generation language models in GitHub copilot","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Secur.)","author":"Niu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM55253.2022.00014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512225"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3361661"},{"key":"ref26","article-title":"AWS CodeWhisperer: Features","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00053"},{"key":"ref28","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Nijkamp","year":"2023"},{"key":"ref29","article-title":"codeparrot (codeparrot),\u201d huggingface.co"},{"key":"ref30","article-title":"GPT-Neo: Large scale autoregressive language modeling with mesh-Tensorflow","author":"Black","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/msr.2013.6624029"},{"key":"ref33","first-page":"49","article-title":"Membership inference attacks on sequence-to-sequence models: Is my data in your machine translation system?","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Hisamoto","year":"2020"},{"key":"ref34","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"Proc. USENIX Secur. Symp.","author":"Carlini","year":"2021"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"56","DOI":"10.18653\/v1\/W17-3207","article-title":"Beam search strategies for neural machine translation","volume-title":"Proc. 1st Workshop Neural Mach. Transl.","author":"Freitag","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref37","article-title":"GraphCodeBERT: Pre-training code representations with data flow","volume-title":"Proc. 9th Int. Conf. Learning Representations (ICLR)","author":"Guo"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2983990.2984041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510222"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"6265","DOI":"10.18653\/v1\/2022.acl-long.434","article-title":"An empirical study of memorization in NLP","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics(Volume 1: Long Papers)","author":"Zheng","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/sp46214.2022.9833571"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111774"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5469"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00044"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527897"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3635711"},{"issue":"8","key":"ref50","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/msr59073.2023.00082"},{"key":"ref52","first-page":"1073","article-title":"Big code != big vocabulary: Open-vocabulary models for source code","volume-title":"Proc. IEEE\/ACM 42nd Int. Conf. Softw. Eng. (ICSE)","author":"Karampatsis","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"issue":"4","key":"ref54","first-page":"359","article-title":"An empirical study of smoothing techniques for language modeling","volume-title":"Comput. Speech Lang.","volume":"13","author":"Chen","year":"1999"},{"key":"ref55","article-title":"A massively spiffy yet delicately unobtrusive compression library","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref57","volume-title":"Design and Analysis of Experiments 7th ed.tion with Student Solutions Manual and Design Expert 7. 0. 3 Set","author":"Montgomery","year":"2009"},{"key":"ref58","first-page":"280","article-title":"Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks","volume-title":"Proc. 32nd IEEE\/ACM Int. Conf. on Program. Comp.","author":"Cotroneo","year":"2024"},{"issue":"4","key":"ref59","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0169-7439(89)80095-4","article-title":"Analysis of variance (ANOVA)","volume":"6","author":"St","year":"1989","journal-title":"Chemometrics Intell. Lab. Syst."},{"issue":"6","key":"ref60","first-page":"80","article-title":"Individual comparisons by ranking methods","volume-title":"Biometrics Bull.","volume":"1","author":"Wilcoxon","year":"1945"},{"issue":"89","key":"ref61","volume-title":"Multiple Comparison Procedures","volume":"1993","author":"Toothaker"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e509"},{"key":"ref63","article-title":"Tree-sitter: An incremental parsing library","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09916-6"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3707450"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00024"},{"key":"ref67","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen","year":"1988"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref69","first-page":"1433","article-title":"Mitigating membership inference attacks by $\\{${Self-Distillation$\\}$} through a novel ensemble architecture","volume-title":"Proc. 31st USENIX Secur. Symp. (USENIX Secur.)","author":"Tang","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243855"},{"key":"ref71","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Bengio","year":"2015"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409671"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_60873"},{"key":"ref74","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref75","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. 6th Int. Conf. Learn. Representations (ICLR)","author":"Madry"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2022.3208239"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106552"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678706"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICST49551.2021.00016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26739"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/icpr56361.2022.9956690"},{"key":"ref82","article-title":"Poison attack and defense on deep source code processing models","author":"Li","year":"2022"},{"key":"ref83","first-page":"8332","article-title":"Quantifying privacy risks of masked language models using membership inference attacks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Abu Dhabi","author":"Mireshghallah","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2019.2897554"},{"key":"ref85","article-title":"Thieves on sesame street! model extraction of BERT-based APIs","author":"Krishna","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3453090"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"ref89","article-title":"UCI machine learning repository","author":"Dua","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.2196\/publichealth.7001"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.5555\/3241094.3241142"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417238"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/10794440\/10735776.pdf?arnumber=10735776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T20:49:26Z","timestamp":1734036566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10735776\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":92,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tse.2024.3482719","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}