{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:48:29Z","timestamp":1791460109337,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3793302.3793348","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:42:54Z","timestamp":1785494574000},"page":"169-180","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Secret Leak Detection in Software Issue Reports using LLMs: A Comprehensive Evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4492-2421","authenticated-orcid":false,"given":"Sadif","family":"Ahmed","sequence":"first","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2620-9538","authenticated-orcid":false,"given":"Md Nafiu","family":"Rahman","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7273-4165","authenticated-orcid":false,"given":"Zahin","family":"Wahab","sequence":"additional","affiliation":[{"name":"University of British Columbia, Vancouver, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-095X","authenticated-orcid":false,"given":"Gias","family":"Uddin","sequence":"additional","affiliation":[{"name":"York university, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9540-315X","authenticated-orcid":false,"given":"Rifat","family":"Shahriyar","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Meysam Alizadeh Ma\u00ebl Kubli Zeynab Samei Shirin Dehghani Mohammadmasiha Zahedivafa Juan\u00a0Diego Bermeo Maria Korobeynikova and Fabrizio Gilardi. 2025. Open-Source Large Language Models for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning. Journal of Computational Social Science 8 17 (2025). open access; empirical evaluation of open-source LLMs on text classification tasks.","DOI":"10.1007\/s42001-024-00345-9"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM56168.2023.10304853"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Setu\u00a0Kumar Basak Lorenzo Neil Bradley Reaves and Laurie Williams. 2023. SecretBench: A Dataset of Software Secrets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.06729 (2023).","DOI":"10.1109\/MSR59073.2023.00053"},{"key":"e_1_3_3_2_6_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_7_2","unstructured":"Kevin Clark Minh-Thang Luong Quoc\u00a0V Le and Christopher\u00a0D Manning. 2020. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2003.10555 (2020)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20 1 (1960) 37\u201346.","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_3_2_9_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Dai Zihang","year":"2020","unstructured":"Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc\u00a0V. Le, and Ruslan Salakhutdinov. 2020. Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing. In Advances in Neural Information Processing Systems (NeurIPS). https:\/\/arxiv.org\/abs\/2006.03236"},{"key":"e_1_3_3_2_10_2","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. arxiv:https:\/\/arXiv.org\/abs\/2305.14314\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.14314"},{"key":"e_1_3_3_2_11_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2019). https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_3_2_12_2","unstructured":"Etimad Fadel. 2024. A Performance Evaluation of BERT-Based Models for Text Classification Tasks. International Journal of Technology Management and Humanities (2024). evaluates standard and distilled BERT variants on multiple text classification datasets."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510150"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang et\u00a0al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.08155 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Sally Fincher and Josh Tenenberg. 2005. Making sense of card sorting data. Expert Systems 22 3 (2005) 89\u201393.","DOI":"10.1111\/j.1468-0394.2005.00299.x"},{"key":"e_1_3_3_2_16_2","unstructured":"Bits &\u00a0Bytes Foundation. 2025. AdamW \u2014 bitsandbytes Optimizers. https:\/\/huggingface.co\/docs\/bitsandbytes\/main\/reference\/optim\/adamw. Accessed: 2025-10-23."},{"key":"e_1_3_3_2_17_2","volume-title":"State of Secrets Sprawl Report 2023","year":"2024","unstructured":"GitGuardian. 2024. State of Secrets Sprawl Report 2023. Retrieved 2024-03-12 from https:\/\/www.gitguardian.com\/state-of-secrets-sprawl-report-2023"},{"key":"e_1_3_3_2_18_2","volume-title":"Gitleaks","year":"2018","unstructured":"Gitleaks. 2018. Gitleaks. Accessed: 2024-02-02."},{"key":"e_1_3_3_2_19_2","volume-title":"Gemini 2.0 Flash Model Card","author":"DeepMind Google","year":"2024","unstructured":"Google DeepMind. 2024. Gemini 2.0 Flash Model Card. Technical Report. Google. https:\/\/modelcards.withgoogle.com\/assets\/documents\/gemini-2-flash.pdf Accessed: January 2026."},{"key":"e_1_3_3_2_20_2","volume-title":"Cryptojackers steal AWS credentials from GitHub in 5 minutes","author":"Jones Connor","year":"2023","unstructured":"Connor Jones. 2023. Cryptojackers steal AWS credentials from GitHub in 5 minutes. Accessed: 2024-02-02."},{"key":"e_1_3_3_2_21_2","unstructured":"Arina Kostina Marios\u00a0D. Dikaiakos Dimosthenis Stefanidis and George Pallis. 2025. Large Language Models For Text Classification: Case Study And Comprehensive Review. arxiv:https:\/\/arXiv.org\/abs\/2501.08457\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.08457"},{"key":"e_1_3_3_2_22_2","volume-title":"The secrets about exposed secrets in code","author":"Kreichman Igal","year":"2021","unstructured":"Igal Kreichman. 2021. The secrets about exposed secrets in code. Accessed: 2024-02-02."},{"key":"e_1_3_3_2_23_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations. In International Conference on Learning Representations (ICLR). https:\/\/arxiv.org\/abs\/1909.11942"},{"key":"e_1_3_3_2_24_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.11692 (2019)."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23418"},{"key":"e_1_3_3_2_26_2","volume-title":"gitrob","year":"2014","unstructured":"Michenriksen. 2014. gitrob. Retrieved 2024-03-26 from https:\/\/github.com\/michenriksen\/gitrob"},{"key":"e_1_3_3_2_27_2","unstructured":"Paulius Micikevicius Sharan Narang Jonah Alben Gregory Diamos Erich Elsen David Garcia Boris Ginsburg Michael Houston Oleksii Kuchaiev Ganesh Venkatesh and Hao Wu. 2018. Mixed Precision Training. arxiv:https:\/\/arXiv.org\/abs\/1710.03740\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/1710.03740"},{"key":"e_1_3_3_2_28_2","unstructured":"Matthew\u00a0B Miles. 1994. Qualitative data analysis: An expanded sourcebook. Thousand Oaks (1994)."},{"key":"e_1_3_3_2_29_2","unstructured":"Thu-Trang Nguyen Thanh\u00a0Trong Vu Hieu\u00a0Dinh Vo and Son Nguyen. 2024. An Empirical Study on Capability of Large Language Models in Understanding Code Semantics. arxiv:https:\/\/arXiv.org\/abs\/2407.03611\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.03611"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Md\u00a0Nafiu Rahman Sadif Ahmed Zahin Wahab S\u00a0M Sohan and Rifat Shahriyar. 2025. Secret Breach Detection in Source Code with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.18784 (2025). https:\/\/arxiv.org\/abs\/2504.18784","DOI":"10.1109\/ESEM64174.2025.00021"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS48256.2020.9027350"},{"key":"e_1_3_3_2_32_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. CoRR abs\/1910.01108 (2019). https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2015.48"},{"key":"e_1_3_3_2_34_2","volume-title":"Sophos 2023 Threat Report","year":"2023","unstructured":"Sophos. 2023. Sophos 2023 Threat Report. Accessed: 2024-03-21."},{"key":"e_1_3_3_2_35_2","volume-title":"TruffleHog","year":"2016","unstructured":"TruffleSecurity. 2016. TruffleHog. Accessed: 2024-02-02."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Zhiqiang Wang Yiran Pang Yanbin Lin and Xingquan Zhu. 2024. Adaptable and Reliable Text Classification using Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.10523 (2024). evaluates LLMs for text classification tasks.","DOI":"10.1109\/ICDMW65004.2024.00015"},{"key":"e_1_3_3_2_37_2","unstructured":"Lingling Xu Haoran Xie Si-Zhao\u00a0Joe Qin Xiaohui Tao and Fu\u00a0Lee Wang. 2023. Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment. arxiv:https:\/\/arXiv.org\/abs\/2312.12148\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2312.12148"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Ikuya Yamada Akari Asai Hiroyuki Shindo Hideaki Takeda and Yuji Matsumoto. 2020. LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention. CoRR abs\/2010.01057 (2020). https:\/\/arxiv.org\/abs\/2010.01057","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"e_1_3_3_2_39_2","unstructured":"Zhilin Yang Zihang Dai Yiming Yang Jaime Carbonell Russ\u00a0R Salakhutdinov and Quoc\u00a0V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_40_2","unstructured":"Davis Yoshida. 2023. NF4 Isn\u2019t Information Theoretically Optimal (and that\u2019s Good). arxiv:https:\/\/arXiv.org\/abs\/2306.06965\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2306.06965"},{"key":"e_1_3_3_2_41_2","unstructured":"Manzil Zaheer Guru Guruganesh Avinava Dubey Joshua Ainslie Chris Alberti Santiago Ontanon Philip Pham Anirudh Ravula Qifan Wang Li Yang and Amr Ahmed. 2021. Big Bird: Transformers for Longer Sequences. arxiv:https:\/\/arXiv.org\/abs\/2007.14062\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2007.14062"},{"key":"e_1_3_3_2_42_2","unstructured":"Yilun Zhu Joel Ruben\u00a0Antony Moniz Shruti Bhargava Jiarui Lu Dhivya Piraviperumal Site Li Yuan Zhang Hong Yu and Bo-Hsiang Tseng. 2024. Can Large Language Models Understand Context? arxiv:https:\/\/arXiv.org\/abs\/2402.00858\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2402.00858"}],"event":{"name":"MSR '26: 23rd International Conference on Mining Software Repositories","location":"Rio de Janeiro Brazil","acronym":"MSR '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 23rd International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793302.3793348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:44:46Z","timestamp":1785494686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793302.3793348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":41,"alternative-id":["10.1145\/3793302.3793348","10.1145\/3793302"],"URL":"https:\/\/doi.org\/10.1145\/3793302.3793348","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}