{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:17:23Z","timestamp":1783408643087,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786181.3788719","type":"proceedings-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:28:24Z","timestamp":1783405704000},"page":"175-183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4213-9940","authenticated-orcid":false,"given":"Arastoo","family":"Zibaeirad","sequence":"first","affiliation":[{"name":"University of North Carolina at Charlotte, Charlotte, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5103-8541","authenticated-orcid":false,"given":"Marco","family":"Vieira","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte, Charlotte, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Vahid Babaey and Hamid\u00a0Reza Faragardi. 2025. Detecting Zero-Day Web Attacks Using One-Class Ensemble Classifiers. (2025).","DOI":"10.20944\/preprints202503.0257.v1"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Vahid Babaey and Arun Ravindran. 2024. Gensqli: A generative artificial intelligence framework for automatically securing web application firewalls against structured query language injection attacks. Future Internet 17 1 (2024) 8.","DOI":"10.3390\/fi17010008"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Vahid Babaey and Arun Ravindran. 2025. GenXSS: an AI-Driven Framework for Automated Detection of XSS Attacks in WAFs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.08176 (2025).","DOI":"10.20944\/preprints202503.0313.v1"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978428"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3652136"},{"key":"e_1_3_3_1_7_2","unstructured":"Thomas\u00a0G Dietterich et\u00a0al. 2002. Ensemble learning. The handbook of brain theory and neural networks 2 1 (2002) 110\u2013125."},{"key":"e_1_3_3_1_8_2","unstructured":"Yangruibo Ding Yanjun Fu Omniyyah Ibrahim Chawin Sitawarin Xinyun Chen Basel Alomair David Wagner Baishakhi Ray and Yizheng Chen. 2024. Vulnerability detection with code language models: How far are we?arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.18624 (2024)."},{"key":"e_1_3_3_1_9_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The Llama 3 Herd of Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00040"},{"key":"e_1_3_3_1_11_2","unstructured":"Zeyu Gao Hao Wang Yuchen Zhou Wenyu Zhu and Chao Zhang. 2023. How Far Have We Gone in Vulnerability Detection Using Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.12420 (2023)."},{"key":"e_1_3_3_1_12_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier et\u00a0al. 2023. Mistral 7B. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06825 (2023)."},{"key":"e_1_3_3_1_13_2","unstructured":"Avishree Khare Saikat Dutta Ziyang Li Alaia Solko-Breslin Rajeev Alur and Mayur Naik. 2023. Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.16169 (2023)."},{"key":"e_1_3_3_1_14_2","unstructured":"Ziyang Li Saikat Dutta and Mayur Naik. 2024. LLM-Assisted Static Analysis for Detecting Security Vulnerabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17238 (2024)."},{"key":"e_1_3_3_1_15_2","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_3_1_16_2","unstructured":"Ruitong Liu Yanbin Wang Haitao Xu Bin Liu Jianguo Sun Zhenhao Guo and Wenrui Ma. 2024. Source Code Vulnerability Detection: Combining Code Language Models and Code Property Graphs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.14719 (2024)."},{"key":"e_1_3_3_1_17_2","unstructured":"Yu Liu Lang Gao Mingxin Yang Yu Xie Ping Chen Xiaojin Zhang and Wei Chen. 2024. VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.07595 (2024)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639142"},{"key":"e_1_3_3_1_19_2","unstructured":"Qiheng Mao Zhenhao Li Xing Hu Kui Liu Xin Xia and Jianling Sun. 2024. Towards Effectively Detecting and Explaining Vulnerabilities Using Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09701 (2024)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Thomas\u00a0J McCabe. 1976. A complexity measure. IEEE Transactions on software Engineering4 (1976) 308\u2013320.","DOI":"10.1109\/TSE.1976.233837"},{"key":"e_1_3_3_1_21_2","first-page":"311","volume-title":"40th annual meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Hammond Pearce Baleegh Ahmad Benjamin Tan Brendan Dolan-Gavitt and Ramesh Karri. 2025. Asleep at the keyboard? assessing the security of github copilot\u2019s code contributions. Commun. ACM 68 2 (2025) 96\u2013105.","DOI":"10.1145\/3610721"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00174"},{"key":"e_1_3_3_1_25_2","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.10297 (2020)."},{"key":"e_1_3_3_1_26_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing\u00a0Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et\u00a0al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.12950 (2023)."},{"key":"e_1_3_3_1_27_2","unstructured":"Yuqiang Sun Daoyuan Wu Yue Xue Han Liu Wei Ma Lyuye Zhang Miaolei Shi and Yang Liu. 2024. LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs\u2019 Vulnerability Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.16185 (2024)."},{"key":"e_1_3_3_1_28_2","unstructured":"Gemma Team Thomas Mesnard Cassidy Hardin Robert Dadashi Surya Bhupatiraju Shreya Pathak Laurent Sifre Morgane Rivi\u00e8re Mihir\u00a0Sanjay Kale Juliette Love et\u00a0al. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.08295 (2024)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00210"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639212"},{"key":"e_1_3_3_1_31_2","unstructured":"Huanting Wang Guixin Ye Zhanyong Tang Shin\u00a0Hwei Tan Songfang Huang Dingyi Fang Yansong Feng Lizhong Bian and Zheng Wang. 2020. Combining graph-based learning with automated data collection for code vulnerability detection. IEEE Transactions on Information Forensics and Security 16 (2020) 1943\u20131958."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00191"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_3_1_34_2","unstructured":"Xin Zhou Sicong Cao Xiaobing Sun and David Lo. 2024. Large Language Model for Vulnerability Detection and Repair: Literature Review and Roadmap. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02525 (2024)."},{"key":"e_1_3_3_1_35_2","unstructured":"Yaqin Zhou Shangqing Liu Jingkai Siow Xiaoning Du and Yang Liu. 2019. Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_36_2","unstructured":"Arastoo Zibaeirad Farnoosh Koleini Shengping Bi Tao Hou and Tao Wang. 2024. A comprehensive survey on the security of smart grid: Challenges mitigations and future research opportunities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.07966 (2024)."},{"key":"e_1_3_3_1_37_2","unstructured":"Arastoo Zibaeirad and Marco Vieira. 2024. VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.10756 (2024)."},{"key":"e_1_3_3_1_38_2","unstructured":"Arastoo Zibaeirad and Marco Vieira. 2025. Reasoning with LLMs for Zero-Shot Vulnerability Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.17885 (2025)."}],"event":{"name":"LLM4Code '26: 3rd International Workshop on Large Language Models For Code","location":"Rio de Janeiro Brazil","acronym":"LLM4Code '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 3rd International Workshop on Large Language Models For Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:33:00Z","timestamp":1783405980000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786181.3788719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":37,"alternative-id":["10.1145\/3786181.3788719","10.1145\/3786181"],"URL":"https:\/\/doi.org\/10.1145\/3786181.3788719","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}