{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:59:10Z","timestamp":1772830750365,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"U.S. National Science Foundation (NSF)","award":["2313054"],"award-info":[{"award-number":["2313054"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639170","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Towards Causal Deep Learning for Vulnerability Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2680-2309","authenticated-orcid":false,"given":"Md Mahbubur","family":"Rahman","sequence":"first","affiliation":[{"name":"Iowa State University, Ames, Iowa, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4697-5586","authenticated-orcid":false,"given":"Ira","family":"Ceka","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2649-3368","authenticated-orcid":false,"given":"Chengzhi","family":"Mao","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6889-7171","authenticated-orcid":false,"given":"Saikat","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, Washington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-5235","authenticated-orcid":false,"given":"Baishakhi","family":"Ray","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6797-0648","authenticated-orcid":false,"given":"Wei","family":"Le","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, Iowa, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"d.]. Cybercrime To Cost The World $10.5 Trillion Annually By","year":"2025","unstructured":"[n. d.]. Cybercrime To Cost The World $10.5 Trillion Annually By 2025, howpublished =https:\/\/cybersecurityventures.com\/hackerpocalypse-cybercrime-report-2016\/."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Microsoft Exchange Flaw: Attacks Surge After Code Published howpublished =https:\/\/www.bankinfosecurity.com\/ms-exchange-flaw-causes-spike-intrdownloader-gen-trojans-a-16236."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"2022. NatGen: Generative Pre-training by \"Naturalizing\" Source Code - Code and scripts for Pre-Training. 10.5281\/zenodo.6977595","DOI":"10.5281\/zenodo.6977595"},{"key":"e_1_3_2_1_4_1","volume-title":"Unified Pre-training for Program Understanding and Generation. In 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).","author":"Ahmad Wasi Uddin","year":"2021","unstructured":"Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. In 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510219"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3087402"},{"key":"e_1_3_2_1_8_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_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510457.3513081"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.436"},{"key":"e_1_3_2_1_11_1","volume-title":"TRACED: Execution-aware Pre-training for Source Code. arXiv:2306.07487 [cs.SE]","author":"Ding Yangruibo","year":"2023","unstructured":"Yangruibo Ding, Ben Steenhoek, Kexin Pei, Gail Kaiser, Wei Le, and Baishakhi Ray. 2023. TRACED: Execution-aware Pre-training for Source Code. arXiv:2306.07487 [cs.SE]"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387501"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528452"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Daya Guo Shuai Lu Nan Duan Yanlin Wang Ming Zhou and Jian Yin. 2022. UniXcoder: Unified Cross-Modal Pre-training for Code Representation. arXiv:2203.03850 [cs.CL]","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_1_16_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations.","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Jian Yin, Daxin Jiang, et al. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3527949"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519575"},{"key":"e_1_3_2_1_19_1","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin Clement Dawn Drain Daxin Jiang Duyu Tang et al. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. arXiv preprint arXiv:2102.04664 (2021). https:\/\/arxiv.org\/abs\/2102.04664"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00737"},{"key":"e_1_3_2_1_21_1","volume-title":"Causality: Models, reasoning, and inference.","author":"Pearl Judea","year":"2000","unstructured":"Judea Pearl. 2000. Causality: Models, reasoning, and inference."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2011.169"},{"key":"e_1_3_2_1_23_1","volume-title":"Richard Jiles, and Wei Le.","author":"Steenhoek Benjamin","year":"2023","unstructured":"Benjamin Steenhoek, Md Mahbubur Rahman, Richard Jiles, and Wei Le. 2023. An Empirical Study of Deep Learning Models for Vulnerability Detection. arXiv:2212.08109 [cs.SE]"},{"key":"e_1_3_2_1_24_1","volume-title":"Dan Roth, and Bing Xiang.","author":"Wang Shiqi","year":"2022","unstructured":"Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, and Bing Xiang. 2022. ReCode: Robustness Evaluation of Code Generation Models. arXiv:2212.10264 [cs.LG]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00189"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534223"},{"key":"e_1_3_2_1_27_1","first-page":"10197","article-title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","volume":"32","author":"Zhou Yaqin","year":"2019","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. In Advances in Neural Information Processing Systems, Vol. 32. 10197--10207.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639170","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:12Z","timestamp":1750286952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":27,"alternative-id":["10.1145\/3597503.3639170","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639170","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}