{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:30:09Z","timestamp":1783701009048,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3733799.3762964","type":"proceedings-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:38:49Z","timestamp":1767094729000},"page":"28-39","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2626-3434","authenticated-orcid":false,"given":"Tamas","family":"Bisztray","sequence":"first","affiliation":[{"name":"University of Oslo, Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0095-106X","authenticated-orcid":false,"given":"Bilel","family":"Cherif","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3951-1932","authenticated-orcid":false,"given":"Richard A.","family":"Dubniczky","sequence":"additional","affiliation":[{"name":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7360-8314","authenticated-orcid":false,"given":"Nils","family":"Gruschka","sequence":"additional","affiliation":[{"name":"University of Oslo, Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8718-8285","authenticated-orcid":false,"given":"Bertalan","family":"Borsos","sequence":"additional","affiliation":[{"name":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0632-3172","authenticated-orcid":false,"given":"Mohamed Amine","family":"Ferrag","sequence":"additional","affiliation":[{"name":"United Arab Emirates University, Al Ain, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1858-7618","authenticated-orcid":false,"given":"Attila","family":"Kovacs","sequence":"additional","affiliation":[{"name":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1097-0599","authenticated-orcid":false,"given":"Vasileios","family":"Mavroeidis","sequence":"additional","affiliation":[{"name":"University of Oslo, Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9002-5935","authenticated-orcid":false,"given":"Norbert","family":"Tihanyi","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Abu dhabi, United Arab Emirates and E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243738"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Mohammed Abuhamad Tamer Abuhmed David Mohaisen and Daehun Nyang. 2021. Large-scale and Robust Code Authorship Identification with Deep Feature Learning. ACM Trans. Priv. Secur. 24 4 (July 2021) 23:1\u201323:35. 10.1145\/3461666","DOI":"10.1145\/3461666"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Mohammed Abuhamad Ji-su Rhim Tamer AbuHmed Sana Ullah Sanggil Kang and DaeHun Nyang. 2019. Code authorship identification using convolutional neural networks. Future Generation Computer Systems 95 (June 2019) 104\u2013115. 10.1016\/j.future.2018.12.038","DOI":"10.1016\/j.future.2018.12.038"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Uri Alon Meital Zilberstein Omer Levy and Eran Yahav. 2018. code2vec: Learning Distributed Representations of Code. 10.48550\/arXiv.1803.09473arXiv:https:\/\/arXiv.org\/abs\/1803.09473 [cs].","DOI":"10.48550\/arXiv.1803.09473"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66402-66"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"David \u00c1lvarez Fidalgo and Francisco Ortin. 2025. CLAVE: A deep learning model for source code authorship verification with contrastive learning and transformer encoders. Inf. Process. Manage. 62 3 (April 2025) 16\u00a0pages. 10.1016\/j.ipm.2024.104005","DOI":"10.1016\/j.ipm.2024.104005"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. 10.48550\/arXiv.2309.16609arXiv:https:\/\/arXiv.org\/abs\/2309.16609 [cs].","DOI":"10.48550\/arXiv.2309.16609"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Dimitris Bamidis Ilias Kalouptsoglou Apostolos Ampatzoglou and Alexandros Chatzigeorgiou. 2024. Software Skills Identification: A Multi-Class Classification on Source Code Using Machine Learning. Global Clinical Engineering Journal 6 SI6 (Dec. 2024) 74\u201377. 10.31354\/globalce.v6iSI6.278","DOI":"10.31354\/globalce.v6iSI6.278"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE53047.2021.9569061"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Iz Beltagy Matthew\u00a0E. Peters and Arman Cohan. 2020. Longformer: The Long-Document Transformer. 10.48550\/arXiv.2004.05150arXiv:https:\/\/arXiv.org\/abs\/2004.05150 [cs].","DOI":"10.48550\/arXiv.2004.05150"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005650"},{"key":"e_1_3_3_2_13_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25\u00a0pages."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23304"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/2831143.2831160"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Soohyeon Choi Yong\u00a0Kiam Tan Mark\u00a0Huasong Meng Mohamed Ragab Soumik Mondal David Mohaisen and Khin Mi\u00a0Mi Aung. 2025. I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution. 10.48550\/arXiv.2501.08165arXiv:https:\/\/arXiv.org\/abs\/2501.08165 [cs] version: 1.","DOI":"10.48550\/arXiv.2501.08165"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2011.26"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3558489.3559069"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Arghavan\u00a0Moradi Dakhel Michel\u00a0C. Desmarais and Foutse Khomh. 2023. Dev2vec: Representing Domain Expertise of Developers in an Embedding Space. Information and Software Technology 159 (July 2023) 107218. 10.1016\/j.infsof.2023.107218arXiv:https:\/\/arXiv.org\/abs\/2207.05132 [cs].","DOI":"10.1016\/j.infsof.2023.107218"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Sumanth Dathathri Abigail See Sumedh Ghaisas Po-Sen Huang Rob McAdam Johannes Welbl Vandana Bachani Alex Kaskasoli Robert Stanforth Tatiana Matejovicova Jamie Hayes Nidhi Vyas Majd\u00a0Al Merey Jonah Brown-Cohen Rudy Bunel Borja Balle Taylan Cemgil Zahra Ahmed Kitty Stacpoole Ilia Shumailov Ciprian Baetu Sven Gowal Demis Hassabis and Pushmeet Kohli. 2024. Scalable watermarking for identifying large language model outputs. Nature 634 8035 (Oct. 2024) 818\u2013823. 10.1038\/s41586-024-08025-4Publisher: Nature Publishing Group.","DOI":"10.1038\/s41586-024-08025-4"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0757-77"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang and Ming Zhou. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. 10.48550\/arXiv.2002.08155arXiv:https:\/\/arXiv.org\/abs\/2002.08155 [cs].","DOI":"10.48550\/arXiv.2002.08155"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2016.70"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1134285.1134445"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-34224-959"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Jason Gray Daniele Sgandurra Lorenzo Cavallaro and Jorge Blasco\u00a0Alis. 2024. Identifying Authorship in Malicious Binaries: Features Challenges & Datasets. ACM Comput. Surv. 56 8 Article 212 (April 2024) 36\u00a0pages. 10.1145\/3653973","DOI":"10.1145\/3653973"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Alexey Svyatkovskiy Shengyu Fu Michele Tufano Shao\u00a0Kun Deng Colin Clement Dawn Drain Neel Sundaresan Jian Yin Daxin Jiang and Ming Zhou. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. 10.48550\/arXiv.2009.08366arXiv:https:\/\/arXiv.org\/abs\/2009.08366 [cs].","DOI":"10.48550\/arXiv.2009.08366"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6372-7_70"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Hanxi Guo Siyuan Cheng Kaiyuan Zhang Guangyu Shen and Xiangyu Zhang. 2025. CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs. 10.48550\/arXiv.2506.11059arXiv:https:\/\/arXiv.org\/abs\/2506.11059 [cs].","DOI":"10.48550\/arXiv.2506.11059"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Surbhi Gupta Neeraj Mohan and Munish Kumar. 2021. A Study on Source Device Attribution Using Still Images. Archives of Computational Methods in Engineering 28 4 (June 2021) 2209\u20132223. 10.1007\/s11831-020-09452-y","DOI":"10.1007\/s11831-020-09452-y"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER64311.2025.00044"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Pengcheng He Jianfeng Gao and Weizhu Chen. 2023. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. 10.48550\/arXiv.2111.09543arXiv:https:\/\/arXiv.org\/abs\/2111.09543 [cs].","DOI":"10.48550\/arXiv.2111.09543"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Xie He Arash\u00a0Habibi Lashkari Nikhill Vombatkere and Dilli\u00a0Prasad Sharma. 2024. Authorship Attribution Methods Challenges and Future Research Directions: A Comprehensive Survey. Information 15 3 (March 2024) 131. 10.3390\/info15030131Number: 3 Publisher: Multidisciplinary Digital Publishing Institute.","DOI":"10.3390\/info15030131"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Baixiang Huang Canyu Chen and Kai Shu. 2025. Authorship Attribution in the Era of LLMs: Problems Methodologies and Challenges. 10.48550\/arXiv.2408.08946arXiv:https:\/\/arXiv.org\/abs\/2408.08946 [cs] version: 2.","DOI":"10.48550\/arXiv.2408.08946"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Vaibhavi Kalgutkar Ratinder Kaur Hugo Gonzalez Natalia Stakhanova and Alina Matyukhina. 2019. Code Authorship Attribution: Methods and Challenges. ACM Comput. Surv. 52 1 (Feb. 2019) 3:1\u20133:36. 10.1145\/3292577","DOI":"10.1145\/3292577"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10394237"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Jungin Kim Shinwoo Park and Yo-Sub Han. 2025. Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code. 10.48550\/arXiv.2502.18851arXiv:https:\/\/arXiv.org\/abs\/2502.18851 [cs].","DOI":"10.48550\/arXiv.2502.18851"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Tharindu Kumarage Garima Agrawal Paras Sheth Raha Moraffah Aman Chadha Joshua Garland and Huan Liu. 2024. A Survey of AI-generated Text Forensic Systems: Detection Attribution and Characterization. 10.48550\/arXiv.2403.01152arXiv:https:\/\/arXiv.org\/abs\/2403.01152 [cs] version: 1.","DOI":"10.48550\/arXiv.2403.01152"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Boquan Li Mengdi Zhang Peixin Zhang Jun Sun and Xingmei Wang. 2024. Resilient Watermarking for LLM-Generated Codes. 10.48550\/arXiv.2402.07518arXiv:https:\/\/arXiv.org\/abs\/2402.07518 [cs] version: 1.","DOI":"10.48550\/arXiv.2402.07518"},{"key":"e_1_3_3_2_42_2","unstructured":"Jiawei Liu Chunqiu\u00a0Steven Xia Yuyao Wang and Lingming Zhang. 2023. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation. Advances in Neural Information Processing Systems 36 (Dec. 2023) 21558\u201321572."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","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. 10.48550\/arXiv.1907.11692arXiv:https:\/\/arXiv.org\/abs\/1907.11692 [cs].","DOI":"10.48550\/arXiv.1907.11692"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"T.J. McCabe. 1976. A Complexity Measure. IEEE Transactions on Software Engineering SE-2 4 (1976) 308\u2013320. 10.1109\/TSE.1976.233837","DOI":"10.1109\/TSE.1976.233837"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","unstructured":"Eric Mitchell Yoonho Lee Alexander Khazatsky Christopher\u00a0D. Manning and Chelsea Finn. 2023. DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature. 10.48550\/arXiv.2301.11305arXiv:https:\/\/arXiv.org\/abs\/2301.11305 [cs].","DOI":"10.48550\/arXiv.2301.11305"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Phuong\u00a0T. Nguyen Juri Di\u00a0Rocco Claudio Di\u00a0Sipio Riccardo Rubei Davide Di\u00a0Ruscio and Massimiliano Di\u00a0Penta. 2024. GPTSniffer: A CodeBERT-based classifier to detect source code written by ChatGPT. Journal of Systems and Software 214 (Aug. 2024) 112059. 10.1016\/j.jss.2024.112059","DOI":"10.1016\/j.jss.2024.112059"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Timothy Paek and Chilukuri Mohan. 2025. Detection of LLM-Generated Java Code Using Discretized Nested Bigrams. 10.48550\/arXiv.2502.15740arXiv:https:\/\/arXiv.org\/abs\/2502.15740 [cs].","DOI":"10.48550\/arXiv.2502.15740"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Wei\u00a0Hung Pan Ming\u00a0Jie Chok Jonathan Leong\u00a0Shan Wong Yung\u00a0Xin Shin Yeong\u00a0Shian Poon Zhou Yang Chun\u00a0Yong Chong David Lo and Mei\u00a0Kuan Lim. 2024. Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education. 10.48550\/arXiv.2401.03676arXiv:https:\/\/arXiv.org\/abs\/2401.03676 [cs].","DOI":"10.48550\/arXiv.2401.03676"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Shinwoo Park Hyundong Jin Jeong-won Cha and Yo-Sub Han. 2025. Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features. 10.48550\/arXiv.2502.17749arXiv:https:\/\/arXiv.org\/abs\/2502.17749 [cs] version: 2.","DOI":"10.48550\/arXiv.2502.17749"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/3361338.3361372"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23822-210"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. 10.48550\/arXiv.1910.01108arXiv:https:\/\/arXiv.org\/abs\/1910.01108 [cs].","DOI":"10.48550\/arXiv.1910.01108"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","unstructured":"Yanir Seroussi Ingrid Zukerman and Fabian Bohnert. 2014. Authorship Attribution with Topic Models. Computational Linguistics 40 2 (June 2014) 269\u2013310. 10.1162\/COLIa00173Place: Cambridge MA Publisher: MIT Press.","DOI":"10.1162\/COLIa00173"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-srw.26"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00120"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"Qige Song Yongzheng Zhang Linshu Ouyang and Yige Chen. 2022. BinMLM: Binary Authorship Verification with Flow-aware Mixture-of-Shared Language Model. 10.48550\/arXiv.2203.04472arXiv:https:\/\/arXiv.org\/abs\/2203.04472 [cs].","DOI":"10.48550\/arXiv.2203.04472"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Hyunjae Suh Mahan Tafreshipour Jiawei Li Adithya Bhattiprolu and Iftekhar Ahmed. 2024. An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?10.48550\/arXiv.2411.04299arXiv:https:\/\/arXiv.org\/abs\/2411.04299 [cs] version: 1.","DOI":"10.48550\/arXiv.2411.04299"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","unstructured":"Tarun Suresh Shubham Ugare Gagandeep Singh and Sasa Misailovic. 2025. Is The Watermarking Of LLM-Generated Code Robust?10.48550\/arXiv.2403.17983arXiv:https:\/\/arXiv.org\/abs\/2403.17983 [cs].","DOI":"10.48550\/arXiv.2403.17983"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSINTESA62455.2024.10748227"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","unstructured":"Norbert Tihanyi Tamas Bisztray Mohamed\u00a0Amine Ferrag Ridhi Jain and Lucas\u00a0C. Cordeiro. 2024. How secure is AI-generated code: a large-scale comparison of large language models. Empirical Software Engineering 30 2 (Dec. 2024) 47. 10.1007\/s10664-024-10590-1","DOI":"10.1007\/s10664-024-10590-1"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Farhan Ullah Muhammad\u00a0Rashid Naeem Hamad Naeem Xiaochun Cheng and Mamoun Alazab. 2022. CroLSSim: Cross-language software similarity detector using hybrid approach of LSA-based AST-MDrep features and CNN-LSTM model. International Journal of Intelligent Systems 37 9 (2022) 5768\u20135795. 10.1002\/int.22813_eprint: https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/int.22813.","DOI":"10.1002\/int.22813"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3270101.3270110"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven C.\u00a0H. Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. 10.48550\/arXiv.2109.00859arXiv:https:\/\/arXiv.org\/abs\/2109.00859 [cs].","DOI":"10.48550\/arXiv.2109.00859"},{"key":"e_1_3_3_2_65_2","unstructured":"Benjamin Warner Antoine Chaffin Benjamin Clavi\u00e9 Orion Weller Oskar Hallstr\u00f6m Said Taghadouini Alexis Gallagher Raja Biswas Faisal Ladhak Tom Aarsen Nathan Cooper Griffin Adams Jeremy Howard and Iacopo Poli. 2024. Smarter Better Faster Longer: A Modern Bidirectional Encoder for Fast Memory Efficient and Long Context Finetuning and Inference. arxiv:https:\/\/arXiv.org\/abs\/2412.13663\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.13663"},{"key":"e_1_3_3_2_66_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. https:\/\/arxiv.org\/abs\/2201.11903v6"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","unstructured":"Zhenyu Xu and Victor\u00a0S. Sheng. 2025. CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models. 10.48550\/arXiv.2501.03288arXiv:https:\/\/arXiv.org\/abs\/2501.03288 [cs] version: 1.","DOI":"10.48550\/arXiv.2501.03288"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","unstructured":"Sarim Zafar Muhammad\u00a0Usman Sarwar Saeed Salem and Muhammad\u00a0Zubair Malik. 2020. Language and Obfuscation Oblivious Source Code Authorship Attribution. IEEE Access 8 (2020) 197581\u2013197596. 10.1109\/ACCESS.2020.3034932","DOI":"10.1109\/ACCESS.2020.3034932"}],"event":{"name":"AISec '25: Proceedings of the 2025 Workshop on Artificial Intelligence and Security","location":"Taipei , Taiwan","acronym":"AISec '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 18th ACM Workshop on Artificial Intelligence and Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3733799.3762964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:53:01Z","timestamp":1767095581000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733799.3762964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":67,"alternative-id":["10.1145\/3733799.3762964","10.1145\/3733799"],"URL":"https:\/\/doi.org\/10.1145\/3733799.3762964","relation":{},"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"2025-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}