{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:54:07Z","timestamp":1774929247209,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1145\/3639476.3639757","type":"proceedings-article","created":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T15:15:01Z","timestamp":1716563701000},"page":"52-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Re(gEx|DoS)Eval: Evaluating Generated Regular Expressions and their Proneness to DoS Attacks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-3611","authenticated-orcid":false,"given":"Mohammed Latif","family":"Siddiq","sequence":"first","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8379-6871","authenticated-orcid":false,"given":"Jiahao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9854-7437","authenticated-orcid":false,"given":"Lindsay","family":"Roney","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8743-2516","authenticated-orcid":false,"given":"Joanna C. S.","family":"Santos","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2024,5,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. GitHub Copilot. Accessed Dec 7 2022. https:\/\/github.com\/features\/copilot"},{"key":"e_1_3_2_1_2_1","first-page":"2023","article-title":"Chat completions","volume":"25","year":"2023","unstructured":"2023. Chat completions. Accessed Mar 25, 2023. https:\/\/platform.openai.com\/docs\/guides\/chat","journal-title":"Accessed Mar"},{"key":"e_1_3_2_1_3_1","volume-title":"re --- Regular expression operations. https:\/\/docs.python.org\/3\/library\/re.html [Online","year":"2023","unstructured":"2023. re --- Regular expression operations. https:\/\/docs.python.org\/3\/library\/re.html [Online; accessed 11. Sep. 2023]."},{"key":"e_1_3_2_1_4_1","volume-title":"https:\/\/learn.snyk.io\/lesson\/redos [Online","author":"Tutorials S","year":"2023","unstructured":"2023. ReDoS | Tutorials & Examples | Snyk Learn. https:\/\/learn.snyk.io\/lesson\/redos [Online; accessed 15. Sep. 2023]."},{"key":"e_1_3_2_1_5_1","volume-title":"Regular Expression Library. https:\/\/regexlib.com [Online","year":"2023","unstructured":"2023. Regular Expression Library. https:\/\/regexlib.com [Online; accessed 11. Sep. 2023]."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2515587"},{"key":"e_1_3_2_1_7_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D 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 Ziegler, Jeffrey Wu, Clemens Winter, Chris 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 Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901."},{"key":"e_1_3_2_1_8_1","volume-title":"CodeT: Code Generation with Generated Tests. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ktrw68Cmu9c","author":"Chen Bei","year":"2023","unstructured":"Bei Chen, Fengji Zhang, Anh Nguyen, Daoguang Zan, Zeqi Lin, Jian-Guang Lou, and Weizhu Chen. 2023. CodeT: Code Generation with Generated Tests. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ktrw68Cmu9c"},{"key":"e_1_3_2_1_9_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_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236027"},{"key":"e_1_3_2_1_11_1","volume-title":"Contamination attacks and mitigation in multi-party machine learning. Advances in neural information processing systems 31","author":"Hayes Jamie","year":"2018","unstructured":"Jamie Hayes and Olga Ohrimenko. 2018. Contamination attacks and mitigation in multi-party machine learning. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Long Short-term Memory. Neural computation 9 (12","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long Short-term Memory. Neural computation 9 (12 1997), 1735--80."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/568438.568455"},{"key":"e_1_3_2_1_14_1","volume-title":"Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks. arXiv preprint arXiv:2305.10160","author":"Jacovi Alon","year":"2023","unstructured":"Alon Jacovi, Avi Caciularu, Omer Goldman, and Yoav Goldberg. 2023. Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks. arXiv preprint arXiv:2305.10160 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Kulal Sumith","year":"2019","unstructured":"Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, and Percy S Liang. 2019. SPoC: Search-based Pseudocode to Code. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_16_1","unstructured":"Nate Kushman and Regina Barzilay. 2013. Using semantic unification to generate regular expressions from natural language. North American Chapter of the Association for Computational Linguistics (NAACL)."},{"key":"e_1_3_2_1_17_1","first-page":"3","article-title":"Synthesizing Regular Expressions from Examples for Introductory Automata Assignments","volume":"52","author":"Lee Mina","year":"2016","unstructured":"Mina Lee, Sunbeom So, and Hakjoo Oh. 2016. Synthesizing Regular Expressions from Examples for Introductory Automata Assignments. SIGPLAN Not. 52, 3 (oct 2016), 70--80.","journal-title":"SIGPLAN Not."},{"key":"e_1_3_2_1_18_1","volume-title":"Suriya Gunasekar, and Yin Tat Lee.","author":"Li Yuanzhi","year":"2023","unstructured":"Yuanzhi Li, S\u00e9bastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. 2023. Textbooks Are All You Need II: phi-1.5 technical report. arXiv:2309.05463 [cs.CL]"},{"key":"e_1_3_2_1_19_1","volume-title":"ReDoSHunter: A Combined Static and Dynamic Approach for Regular Expression DoS Detection. In 30th USENIX Security Symposium (USENIX Security 21)","author":"Li Yeting","year":"2021","unstructured":"Yeting Li, Zixuan Chen, Jialun Cao, Zhiwu Xu, Qiancheng Peng, Haiming Chen, Liyuan Chen, and Shing-Chi Cheung. 2021. ReDoSHunter: A Combined Static and Dynamic Approach for Regular Expression DoS Detection. In 30th USENIX Security Symposium (USENIX Security 21). USENIX Association, 3847--3864."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 43rd International Conference on Software Engineering","author":"Li Yeting","year":"2021","unstructured":"Yeting Li, Shuaimin Li, Zhiwu Xu, Jialun Cao, Zixuan Chen, Yun Hu, Haiming Chen, and Shing-Chi Cheung. 2021. TransRegex: Multi-Modal Regular Expression Synthesis by Generate-and-Repair. In Proceedings of the 43rd International Conference on Software Engineering (Madrid, Spain) (ICSE '21). IEEE Press, 1210--1222."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL)","author":"Locascio Nicholas","year":"2016","unstructured":"Nicholas Locascio, Karthik Narasimhan, Eduardo DeLeon, Nate Kushman, and Regina Barzilay. 2016. Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), Austin, Texas, 1918--1923."},{"key":"e_1_3_2_1_22_1","volume-title":"2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 415--426","author":"Michael Louis G.","year":"2019","unstructured":"Louis G. Michael, James Donohue, James C. Davis, Dongyoon Lee, and Francisco Servant. 2019. Regexes are Hard: Decision-Making, Difficulties, and Risks in Programming Regular Expressions. In 2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 415--426."},{"key":"e_1_3_2_1_23_1","volume-title":"Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). 2450--2462","author":"Nashid Noor","year":"2023","unstructured":"Noor Nashid, Mifta Sintaha, and Ali Mesbah. 2023. Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). 2450--2462."},{"key":"e_1_3_2_1_24_1","volume-title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. ICLR","author":"Nijkamp Erik","year":"2023","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2023. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. ICLR (2023)."},{"key":"e_1_3_2_1_25_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","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. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_26_1","volume-title":"Static analysis for regular expression exponential runtime via substructural logics. CoRR abs\/1405.7058","author":"Rathnayake Asiri","year":"2014","unstructured":"Asiri Rathnayake and Hayo Thielecke. 2014. Static analysis for regular expression exponential runtime via substructural logics. CoRR abs\/1405.7058 (2014)."},{"key":"e_1_3_2_1_27_1","volume-title":"Survey reveals AI's impact on the developer experience | The GitHub Blog. GitHub Blog (June","author":"Shani Inbal","year":"2023","unstructured":"Inbal Shani. 2023. Survey reveals AI's impact on the developer experience | The GitHub Blog. GitHub Blog (June 2023). https:\/\/github.blog\/2023-06-13-survey-reveals-ais-impact-on-the-developer-experience\/#methodology"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238159"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549035.3561184"},{"key":"e_1_3_2_1_30_1","volume-title":"Noshin Ulfat, Fahmid Al Rifat, and Vinicius Carvalho Lopes.","author":"Siddiq Mohammed Latif","year":"2023","unstructured":"Mohammed Latif Siddiq, Joanna C. S. Santos, Ridwanul Hasan Tanvir, Noshin Ulfat, Fahmid Al Rifat, and Vinicius Carvalho Lopes. 2023. Exploring the Effectiveness of Large Language Models in Generating Unit Tests. arXiv:2305.00418 [cs.SE]"},{"key":"e_1_3_2_1_31_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL]"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_33_1","volume-title":"Marijn JH Heule, and Isil Dillig","author":"W\u00fcstholz Valentin","year":"2017","unstructured":"Valentin W\u00fcstholz, Oswaldo Olivo, Marijn JH Heule, and Isil Dillig. 2017. Static detection of DoS vulnerabilities in programs that use regular expressions. In Tools and Algorithms for the Construction and Analysis of Systems: 23rd International Conference, TACAS 2017, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2017, Uppsala, Sweden, April 22--29, 2017, Proceedings, Part II 23. Springer, 3--20."},{"key":"e_1_3_2_1_34_1","volume-title":"CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models. arXiv preprint arXiv:2302.00288","author":"Yu Hao","year":"2023","unstructured":"Hao Yu, Bo Shen, Dezhi Ran, Jiaxin Zhang, Qi Zhang, Yuchi Ma, Guangtai Liang, Ying Li, Tao Xie, and Qianxiang Wang. 2023. CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models. arXiv preprint arXiv:2302.00288 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Shuai Zhang Xiaodong Gu Yuting Chen and Beijun Shen. 2023. InfeRE: Step-by-Step Regex Generation via Chain of Inference.","DOI":"10.1109\/ASE56229.2023.00111"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","author":"Zhong Zexuan","year":"2018","unstructured":"Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, and Dongmei Zhang. 2018. SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 1608--1618."},{"key":"e_1_3_2_1_37_1","volume-title":"AAAI Workshops. 791--794","author":"Zhong Zexuan","year":"2018","unstructured":"Zexuan Zhong, Jiaqi Guo, Wei Yang, Tao Xie, Jian-Guang Lou, Ting Liu, and Dongmei Zhang. 2018. Generating regular expressions from natural language specifications: Are we there yet?. In AAAI Workshops. 791--794."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534864"}],"event":{"name":"ICSE-NIER'24: 2024 ACM\/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results","location":"Lisbon Portugal","acronym":"ICSE-NIER'24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 2024 ACM\/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639476.3639757","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639476.3639757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:53:38Z","timestamp":1750287218000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639476.3639757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"alternative-id":["10.1145\/3639476.3639757","10.1145\/3639476"],"URL":"https:\/\/doi.org\/10.1145\/3639476.3639757","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-05-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}