{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T15:47:50Z","timestamp":1792856870053,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639133","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Traces of Memorisation in Large Language Models for Code"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7338-2044","authenticated-orcid":false,"given":"Ali","family":"Al-Kaswan","sequence":"first","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5093-5523","authenticated-orcid":false,"given":"Maliheh","family":"Izadi","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4850-3312","authenticated-orcid":false,"given":"Arie","family":"van Deursen","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00033"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/NLBSE59153.2023.00008"},{"key":"e_1_3_2_1_3_1","volume-title":"Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge. ArXiv abs\/2302.07735","author":"Al-Kaswan Ali","year":"2023","unstructured":"Ali Al-Kaswan, Maliheh Izadi, and Arie van Deursen. 2023. Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge. ArXiv abs\/2302.07735 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"SecretBench: A Dataset of Software Secrets. arXiv preprint arXiv:2303.06729","author":"Basak Setu Kumar","year":"2023","unstructured":"Setu Kumar Basak, Lorenzo Neil, Bradley Reaves, and Laurie Williams. 2023. SecretBench: A Dataset of Software Secrets. arXiv preprint arXiv:2303.06729 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Lintang Sutawika, Hailey Schoelkopf, Quentin Anthony, Shivanshu Purohit, and Edward Raf.","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, USVSN Sai Prashanth, Lintang Sutawika, Hailey Schoelkopf, Quentin Anthony, Shivanshu Purohit, and Edward Raf. 2023. Emergent and predictable memorization in large language models. arXiv preprint arXiv:2304.11158 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, and Oskar van der Wal.","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, and Oskar van der Wal. 2023. Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling. arXiv:2304.01373 [cs.CL]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5297715"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"e_1_3_2_1_10_1","volume-title":"Extracting training data from diffusion models. arXiv preprint arXiv:2301.13188","author":"Carlini Nicholas","year":"2023","unstructured":"Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramer, Borja Balle, Daphne Ippolito, and Eric Wallace. 2023. Extracting training data from diffusion models. arXiv preprint arXiv:2301.13188 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Quantifying memorization across neural language models. preprint arXiv:2202.07646","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2022. Quantifying memorization across neural language models. preprint arXiv:2202.07646 (2022)."},{"key":"e_1_3_2_1_12_1","first-page":"13263","article-title":"The privacy onion effect: Memorization is relative","volume":"35","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Matthew Jagielski, Chiyuan Zhang, Nicolas Papernot, Andreas Terzis, and Florian Tramer. 2022. The privacy onion effect: Memorization is relative. Advances in Neural Information Processing Systems 35 (2022), 13263--13276.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21). 2633--2650."},{"key":"e_1_3_2_1_14_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.23014"},{"key":"e_1_3_2_1_16_1","volume-title":"Intellectual Property, and Ethics. ArXiv abs\/2304.02839","author":"Choksi Madiha Zahrah","year":"2023","unstructured":"Madiha Zahrah Choksi and David Goedicke. 2023. Whose Text Is It Anyway? Exploring BigCode, Intellectual Property, and Ethics. ArXiv abs\/2304.02839 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1974","author":"Choquette-Choo Christopher A.","year":"2021","unstructured":"Christopher A. Choquette-Choo, Florian Tramer, Nicholas Carlini, and Nicolas Papernot. 2021. Label-Only Membership Inference Attacks. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 1964--1974. https:\/\/proceedings.mlr.press\/v139\/choquette-choo21a.html"},{"key":"e_1_3_2_1_18_1","volume-title":"Towards More Realistic Membership Inference Attacks on Large Diffusion Models. arXiv preprint arXiv:2306.12983","author":"Dubi\u0144ski Jan","year":"2023","unstructured":"Jan Dubi\u0144ski, Antoni Kowalczuk, Stanis\u0142aw Pawlak, Przemys\u0142aw Rokita, Tomasz Trzci\u0144ski, and Pawe\u0142 Morawiecki. 2023. Towards More Realistic Membership Inference Attacks on Large Diffusion Models. arXiv preprint arXiv:2306.12983 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357713.3384290"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_21_1","volume-title":"Encoder: A generative model for code infilling and synthesis. preprint arXiv:2204.05999","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, and Mike Lewis. 2022. Encoder: A generative model for code infilling and synthesis. preprint arXiv:2204.05999 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027","author":"Gao Leo","year":"2020","unstructured":"Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Foundation Models and Fair Use. arXiv preprint arXiv:2303.15715","author":"Henderson Peter","year":"2023","unstructured":"Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, and Percy Liang. 2023. Foundation Models and Fair Use. arXiv preprint arXiv:2303.15715 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2019-0067"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00299"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523273"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.148"},{"key":"e_1_3_2_1_28_1","volume-title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy. arXiv preprint arXiv:2210.17546","author":"Ippolito Daphne","year":"2022","unstructured":"Daphne Ippolito, Florian Tram\u00e8r, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher A Choquette-Choo, and Nicholas Carlini. 2022. Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy. arXiv preprint arXiv:2210.17546 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Shotaro Ishihara. 2023. Training Data Extraction From Pre-trained Language Models: A Survey. arXiv:2305.16157 [cs.CL]","DOI":"10.18653\/v1\/2023.trustnlp-1.23"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510172"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 10697--10707","author":"Kandpal Nikhil","year":"2022","unstructured":"Nikhil Kandpal, Eric Wallace, and Colin Raffel. 2022. Deduplicating training data mitigates privacy risks in language models. In International Conference on Machine Learning. PMLR, 10697--10707."},{"key":"e_1_3_2_1_32_1","volume-title":"Marco D'Ambros, and Romain Robbes.","author":"Karmakar Anjan","year":"2022","unstructured":"Anjan Karmakar, Julian Aron Prenner, Marco D'Ambros, and Romain Robbes. 2022. Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation. arXiv preprint arXiv:2212.02684 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"e_1_3_2_1_34_1","unstructured":"Raymond Li Loubna Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim Qian Liu Evgenii Zheltonozhskii Terry Yue Zhuo Thomas Wang Olivier Dehaene Mishig Davaadorj Joel Lamy-Poirier Jo\u00e3o Monteiro Oleh Shliazhko Nicolas Gontier Nicholas Meade Armel Zebaze Ming-Ho Yee Logesh Kumar Umapathi Jian Zhu Benjamin Lipkin Muhtasham Oblokulov Zhiruo Wang Rudra Murthy Jason Stillerman Siva Sankalp Patel Dmitry Abulkhanov Marco Zocca Manan Dey Zhihan Zhang Nour Fahmy Urvashi Bhattacharyya Wenhao Yu Swayam Singh Sasha Luccioni Paulo Villegas Maxim Kunakov Fedor Zhdanov Manuel Romero Tony Lee Nadav Timor Jennifer Ding Claire Schlesinger Hailey Schoelkopf Jan Ebert Tri Dao Mayank Mishra Alex Gu Jennifer Robinson Carolyn Jane Anderson Brendan Dolan-Gavitt Danish Contractor Siva Reddy Daniel Fried Dzmitry Bahdanau Yacine Jernite Carlos Mu\u00f1oz Ferrandis Sean Hughes Thomas Wolf Arjun Guha Leandro von Werra and Harm de Vries. 2023. StarCoder: may the source be with you! arXiv:2305.06161 [cs.CL]"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_36_1","volume-title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_1_37_1","volume-title":"Analyzing Leakage of Personally Identifiable Information in Language Models. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 346--363","author":"Lukas Nils","year":"2023","unstructured":"Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, and Santiago Zanella-B\u00e9guelin. 2023. Analyzing Leakage of Personally Identifiable Information in Language Models. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 346--363."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.570"},{"key":"e_1_3_2_1_39_1","volume-title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. arXiv preprint","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. arXiv preprint (2022)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3239668"},{"key":"e_1_3_2_1_42_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. [n. d.]. Language Models are Unsupervised Multitask Learners. ([n.d.])."},{"key":"e_1_3_2_1_44_1","unstructured":"Swapnil Sharma Nikita Anand and Kranthi Kiran G. V. 2023. Stochastic Code Generation. arXiv:2304.08243 [cs.CL]"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512225"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"10993","author":"Tan Jasper","unstructured":"Jasper Tan, Daniel LeJeune, Blake Mason, Hamid Javadi, and Richard G. Baraniuk. 2023. A Blessing of Dimensionality in Membership Inference through Regularization. In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 206), Francisco Ruiz, Jennifer Dy, and Jan-Willem van de Meent (Eds.). PMLR, 10968--10993. https:\/\/proceedings.mlr.press\/v206\/tan23b.html"},{"key":"e_1_3_2_1_48_1","first-page":"38274","article-title":"Memorization without overfitting: Analyzing the training dynamics of large language models","volume":"35","author":"Tirumala Kushal","year":"2022","unstructured":"Kushal Tirumala, Aram Markosyan, Luke Zettlemoyer, and Armen Aghajanyan. 2022. Memorization without overfitting: Analyzing the training dynamics of large language models. Advances in Neural Information Processing Systems 35 (2022), 38274--38290.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_1_50_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_51_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824--24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_2_1_53_1","volume-title":"CERT: Continual Pre-training on Sketches for Library-oriented Code Generation. In The 2022 International Joint Conference on Artificial Intelligence.","author":"Zan Daoguang","year":"2022","unstructured":"Daoguang Zan, Bei Chen, Dejian Yang, Zeqi Lin, Minsu Kim, Bei Guan, Yongji Wang, Weizhu Chen, and Jian-Guang Lou. 2022. CERT: Continual Pre-training on Sketches for Library-oriented Code Generation. In The 2022 International Joint Conference on Artificial Intelligence."}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639133","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:12Z","timestamp":1750286952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":52,"alternative-id":["10.1145\/3597503.3639133","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639133","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}