{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T10:27:34Z","timestamp":1791973654370,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3658644.3670344","type":"proceedings-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T12:19:20Z","timestamp":1733746760000},"page":"2251-2265","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["MGTBench: Benchmarking Machine-Generated Text Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3879-9080","authenticated-orcid":false,"given":"Xinlei","family":"He","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9954-587X","authenticated-orcid":false,"given":"Xinyue","family":"Shen","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4504-7108","authenticated-orcid":false,"given":"Zeyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7130-9211","authenticated-orcid":false,"given":"Michael","family":"Backes","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3612-7348","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"ChatGLM. https:\/\/github.com\/THUDM\/ChatGLM-6B."},{"key":"e_1_3_2_1_2_1","unstructured":"Dolly. https:\/\/github.com\/databrickslabs\/dolly."},{"key":"e_1_3_2_1_3_1","unstructured":"GPTZero. https:\/\/gptzero.me\/."},{"key":"e_1_3_2_1_4_1","unstructured":"StableLM. https:\/\/huggingface.co\/stabilityai\/stablelm-tuned-alpha-7b."},{"key":"e_1_3_2_1_5_1","unstructured":"ChatGPT. https:\/\/chat.openai.com\/chat."},{"key":"e_1_3_2_1_6_1","unstructured":"Claude. https:\/\/claude.ai."},{"key":"e_1_3_2_1_7_1","volume-title":"Gpt4all: Training an assistant-style chatbot with large scale data distillation from gpt-3.5-turbo. https:\/\/github.com\/nomic-ai\/gpt4all","author":"Anand Yuvanesh","year":"2023","unstructured":"Yuvanesh Anand, Zach Nussbaum, Brandon Duderstadt, Benjamin Schmidt, and Andriy Mulyar. Gpt4all: Training an assistant-style chatbot with large scale data distillation from gpt-3.5-turbo. https:\/\/github.com\/nomic-ai\/gpt4all, 2023."},{"key":"e_1_3_2_1_8_1","first-page":"817","volume-title":"International Joint Conference on Natural Language Processing (IJCNLP)","author":"Badaskar Sameer","year":"2008","unstructured":"Sameer Badaskar, Sachin Agarwal, and Shilpa Arora. Identifying Real or Fake Articles: Towards better Language Modeling. In International Joint Conference on Natural Language Processing (IJCNLP), pages 817--822. ACL, 2008."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.40"},{"key":"e_1_3_2_1_10_1","volume-title":"Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, and Samuel Weinbach. Gpt-neox-20b: An open-source autoregressive language model. CoRR abs\/2204.06745","author":"Black Sid","year":"2022","unstructured":"Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, and Samuel Weinbach. Gpt-neox-20b: An open-source autoregressive language model. CoRR abs\/2204.06745, 2022."},{"key":"e_1_3_2_1_11_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS). NeurIPS","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. 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 M. 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. Language Models are Few-Shot Learners. In Annual Conference on Neural Information Processing Systems (NeurIPS). NeurIPS, 2020."},{"key":"e_1_3_2_1_12_1","volume-title":"Sicheng Zhu, Bang An, Dinesh Manocha, and Furong Huang. On the Possibilities of AI-Generated Text Detection. CoRR abs\/2304.04736","author":"Chakraborty Souradip","year":"2023","unstructured":"Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, and Furong Huang. On the Possibilities of AI-Generated Text Detection. CoRR abs\/2304.04736, 2023."},{"key":"e_1_3_2_1_13_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew M. Dai Thanumalayan Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou XuezhiWang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. PaLM: Scaling Language Modeling with Pathways. CoRR abs\/2204.02311 2022."},{"key":"e_1_3_2_1_14_1","first-page":"4299","volume-title":"Annual Conference on Neural Information Processing Systems (NIPS)","author":"Christiano Paul F.","year":"2017","unstructured":"Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. Deep Reinforcement Learning from Human Preferences. In Annual Conference on Neural Information Processing Systems (NIPS), pages 4299--4307. NIPS, 2017."},{"key":"e_1_3_2_1_15_1","first-page":"4171","volume-title":"Conference of the North American","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pages 4171--4186. ACL, 2019."},{"key":"e_1_3_2_1_16_1","first-page":"320","volume-title":"Jie Tang. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. In Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Du Zhengxiao","year":"2022","unstructured":"Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 320--335. ACL, 2022."},{"key":"e_1_3_2_1_17_1","first-page":"111","volume-title":"Rush. GLTR: Statistical Detection and Visualization of Generated Text. In Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Gehrmann Sebastian","year":"2019","unstructured":"Sebastian Gehrmann, Hendrik Strobelt, and Alexander M. Rush. GLTR: Statistical Detection and Visualization of Generated Text. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 111--116. ACL, 2019."},{"key":"e_1_3_2_1_18_1","volume-title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection. CoRR abs\/2301.07597","author":"Guo Biyang","year":"2023","unstructured":"Biyang Guo, Xin Zhang, ZiyuanWang, Minqi Jiang, Jinran Nie, Yuxuan Ding, Jianwei Yue, and YupengWu. How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection. CoRR abs\/2301.07597, 2023."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/11861461_10"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.164"},{"key":"e_1_3_2_1_21_1","volume-title":"Ahmad-Reza Sadeghi. DEMASQ: Unmasking the ChatGPT Wordsmith. In Network and Distributed System Security Symposium (NDSS). Internet Society","author":"Kumari Kavita","year":"2024","unstructured":"Kavita Kumari, Alessandro Pegoraro, Hossein Fereidooni, and Ahmad-Reza Sadeghi. DEMASQ: Unmasking the ChatGPT Wordsmith. In Network and Distributed System Security Symposium (NDSS). Internet Society, 2024."},{"key":"e_1_3_2_1_22_1","first-page":"3214","volume-title":"Owain Evans. TruthfulQA: Measuring How Models Mimic Human Falsehoods. In Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Lin Stephanie","year":"2022","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. TruthfulQA: Measuring How Models Mimic Human Falsehoods. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 3214--3252. ACL, 2022."},{"key":"e_1_3_2_1_23_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692, 2019."},{"key":"e_1_3_2_1_24_1","volume-title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature. CoRR abs\/2301.11305","author":"Mitchell Eric","year":"2023","unstructured":"Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning, and Chelsea Finn. DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature. CoRR abs\/2301.11305, 2023."},{"key":"e_1_3_2_1_25_1","volume-title":"Bimal Viswanath. Deepfake Text Detection: Limitations and Opportunities. In IEEE Symposium on Security and Privacy (S&P). IEEE","author":"Pu Jiameng","year":"2023","unstructured":"Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, and Bimal Viswanath. Deepfake Text Detection: Limitations and Opportunities. In IEEE Symposium on Security and Privacy (S&P). IEEE, 2023."},{"key":"e_1_3_2_1_26_1","volume-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford Alec","year":"2016","unstructured":"Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. Improving Language Understanding by Generative Pre-Training. 2016."},{"key":"e_1_3_2_1_27_1","volume-title":"Language Models are Unsupervised Multitask Learners. OpenAI blog","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language Models are Unsupervised Multitask Learners. OpenAI blog, 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"Journal of Machine Learning Research","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, 2020."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"e_1_3_2_1_30_1","volume-title":"Release Strategies and the Social Impacts of Language Models. CoRR abs\/1908.09203","author":"Solaiman Irene","year":"2019","unstructured":"Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, and Jasmine Wang. Release Strategies and the Social Impacts of Language Models. CoRR abs\/1908.09203, 2019."},{"key":"e_1_3_2_1_31_1","volume-title":"Learning to summarize from human feedback. CoRR abs\/2009.01325","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeff Wu, Daniel M. Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F. Christiano. Learning to summarize from human feedback. CoRR abs\/2009.01325, 2020."},{"key":"e_1_3_2_1_32_1","volume-title":"DiWang, and Preslav Nakov. DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text. CoRR abs\/2306.05540","author":"Su Jinyan","year":"2023","unstructured":"Jinyan Su, Terry Yue Zhuo, DiWang, and Preslav Nakov. DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text. CoRR abs\/2306.05540, 2023."},{"key":"e_1_3_2_1_33_1","volume-title":"ChatGPT: The End of Online Exam Integrity? CoRR abs\/2212.09292","author":"Susnjak Teo","year":"2022","unstructured":"Teo Susnjak. ChatGPT: The End of Online Exam Integrity? CoRR abs\/2212.09292, 2022."},{"key":"e_1_3_2_1_34_1","first-page":"8384","volume-title":"Dongwon Lee. Authorship Attribution for Neural Text Generation. In Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Uchendu Adaku","year":"2020","unstructured":"Adaku Uchendu, Thai Le, Kai Shu, and Dongwon Lee. Authorship Attribution for Neural Text Generation. In Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8384--8395. ACL, 2020."},{"key":"e_1_3_2_1_35_1","first-page":"2001","volume-title":"Dongwon Lee. TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation. In Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Uchendu Adaku","year":"2021","unstructured":"Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, and Dongwon Lee. TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation. In Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2001--2016. ACL, 2021."},{"key":"e_1_3_2_1_36_1","first-page":"5998","volume-title":"Annual Conference on Neural Information Processing Systems (NIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is All you Need. In Annual Conference on Neural Information Processing Systems (NIPS), pages 5998--6008. NIPS, 2017."},{"key":"e_1_3_2_1_37_1","volume-title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models. CoRR abs\/2305.15047","author":"Verma Vivek","year":"2023","unstructured":"Vivek Verma, Eve Fleisig, Nicholas Tomlin, and Dan Klein. Ghostbuster: Detecting Text Ghostwritten by Large Language Models. CoRR abs\/2305.15047, 2023."},{"key":"e_1_3_2_1_38_1","volume-title":"William S. Isaac, Sean Legassick, Geoffrey Irving, and Iason Gabriel. Ethical and social risks of harm from Language Models. CoRR abs\/2112.04359","author":"Weidinger Laura","year":"2021","unstructured":"Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, Zac Kenton, Sasha Brown, Will Hawkins, Tom Stepleton, Courtney Biles, Abeba Birhane, Julia Haas, Laura Rimell, Lisa Anne Hendricks, William S. Isaac, Sean Legassick, Geoffrey Irving, and Iason Gabriel. Ethical and social risks of harm from Language Models. CoRR abs\/2112.04359, 2021."},{"key":"e_1_3_2_1_39_1","first-page":"9051","volume-title":"Yejin Choi. Defending Against Neural Fake News. In Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Zellers Rowan","year":"2019","unstructured":"Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. Defending Against Neural Fake News. In Annual Conference on Neural Information Processing Systems (NeurIPS), pages 9051--9062. NeurIPS, 2019."}],"event":{"name":"CCS '24: ACM SIGSAC Conference on Computer and Communications Security","location":"Salt Lake City UT USA","acronym":"CCS '24","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3670344","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658644.3670344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:57:29Z","timestamp":1755842249000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3670344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":39,"alternative-id":["10.1145\/3658644.3670344","10.1145\/3658644"],"URL":"https:\/\/doi.org\/10.1145\/3658644.3670344","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}