{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:00:43Z","timestamp":1777899643628,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Cybersecurity R&D Programme","award":["NCRP25-P04- TAICeN"],"award-info":[{"award-number":["NCRP25-P04- TAICeN"]}]},{"name":"the National Research Foundation, Singapore, and DSO National Laboratories under the AI Singapore Pro- gramme","award":["AISG2-GC-2023-008"],"award-info":[{"award-number":["AISG2-GC-2023-008"]}]},{"name":"NRF Investigatorship","award":["NRF-NRFI06-2020-0001"],"award-info":[{"award-number":["NRF-NRFI06-2020-0001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,20]]},"DOI":"10.1145\/3652032.3657564","type":"proceedings-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:00:08Z","timestamp":1718902808000},"page":"166-177","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5598-4006","authenticated-orcid":false,"given":"Shangqing","family":"Liu","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0044-466X","authenticated-orcid":false,"given":"Wei","family":"Ma","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0393-3709","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-6502","authenticated-orcid":false,"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9080-6865","authenticated-orcid":false,"given":"Ruitao","family":"Feng","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Allamanis Miltiadis","year":"2018","unstructured":"Miltiadis Allamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=BJOFETxR-"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001423"},{"key":"e_1_3_2_1_3_1","unstructured":"CERN. 2007. CPPCheck. http:\/\/cppcheck.sourceforge.net\/"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.50"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3087402"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243849"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICECCS.2019.00012"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/V1"},{"key":"e_1_3_2_1_9_1","volume-title":"John Grundy, and Aditya Ghose.","author":"Dam Hoa Khanh","year":"2017","unstructured":"Hoa Khanh Dam, Truyen Tran, Trang Pham, Shien Wee Ng, John Grundy, and Aditya Ghose. 2017. Automatic feature learning for vulnerability prediction. CoRR, abs\/1708.02368 (2017), arXiv:1708.02368. arxiv:1708.02368"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS-C60940.2023.00017"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00024"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2019"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533048"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_15_1","volume-title":"Structured Neural Summarization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Fernandes Patrick","year":"2019","unstructured":"Patrick Fernandes, Miltiadis Allamanis, and Marc Brockschmidt. 2019. Structured Neural Summarization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=H1ersoRqtm"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528452"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural Message Passing for Quantum Chemistry. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, Doina Precup and Yee Whye Teh (Eds.) (Proceedings of Machine Learning Research, Vol. 70). PMLR, 1263\u20131272. http:\/\/proceedings.mlr.press\/v70\/gilmer17a.html"},{"key":"e_1_3_2_1_18_1","volume-title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training. CoRR, abs\/2002.09024","author":"Gong ChengYue","year":"2020","unstructured":"ChengYue Gong, Tongzheng Ren, Mao Ye, and Qiang Liu. 2020. MaxUp: A Simple Way to Improve Generalization of Neural Network Training. CoRR, abs\/2002.09024 (2020), arXiv:2002.09024. arxiv:2002.09024"},{"key":"e_1_3_2_1_19_1","volume-title":"Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 1024\u20131034. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/5dd9db5e033da9c6fb5ba83c7a7ebea9-Abstract.html"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Norman Mu, Ekin Dogus Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2020. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=S1gmrxHFvB"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3527949"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Paras Jain Ajay Jain Tianjun Zhang Pieter Abbeel Joseph E Gonzalez and Ion Stoica. 2020. Contrastive Code Representation Learning. arXiv preprint arXiv:2007.04973.","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.62"},{"key":"e_1_3_2_1_25_1","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_27_1","unstructured":"Yujia Li Daniel Tarlow Marc Brockschmidt and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493."},{"key":"e_1_3_2_1_28_1","article-title":"SySeVR: A framework for using deep learning to detect software vulnerabilities","author":"Li Zhen","year":"2021","unstructured":"Zhen Li, Deqing Zou, Shouhuai Xu, Hai Jin, Yawei Zhu, and Zhaoxuan Chen. 2021. SySeVR: A framework for using deep learning to detect software vulnerabilities. IEEE Transactions on Dependable and Secure Computing.","journal-title":"IEEE Transactions on Dependable and Secure Computing."},{"key":"e_1_3_2_1_29_1","volume-title":"Vuldeepecker: A deep learning-based system for vulnerability detection. arXiv preprint arXiv:1801.01681.","author":"Li Zhen","year":"2018","unstructured":"Zhen Li, Deqing Zou, Shouhuai Xu, Xinyu Ou, Hai Jin, Sujuan Wang, Zhijun Deng, and Yuyi Zhong. 2018. Vuldeepecker: A deep learning-based system for vulnerability detection. arXiv preprint arXiv:1801.01681."},{"key":"e_1_3_2_1_30_1","volume-title":"VulDeePecker: A Deep Learning-Based System for Vulnerability Detection. In 25th Annual Network and Distributed System Security Symposium (NDSS","author":"Li Zhen","year":"2018","unstructured":"Zhen Li, Deqing Zou, Shouhuai Xu, Xinyu Ou, Hai Jin, Sujuan Wang, Zhijun Deng, and Yuyi Zhong. 2018. VulDeePecker: A Deep Learning-Based System for Vulnerability Detection. In 25th Annual Network and Distributed System Security Symposium (NDSS 2018)."},{"key":"e_1_3_2_1_31_1","article-title":"Software vulnerability discovery via learning multi-domain knowledge bases","author":"Lin Guanjun","year":"2019","unstructured":"Guanjun Lin, Jun Zhang, Wei Luo, Lei Pan, Olivier De Vel, Paul Montague, and Yang Xiang. 2019. Software vulnerability discovery via learning multi-domain knowledge bases. IEEE Transactions on Dependable and Secure Computing.","journal-title":"IEEE Transactions on Dependable and Secure Computing."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3418924"},{"key":"e_1_3_2_1_33_1","unstructured":"Shangqing Liu Yu Chen Xiaofei Xie Jingkai Siow and Yang Liu. 2020. Retrieval-augmented generation for code summarization via hybrid gnn. arXiv preprint arXiv:2006.05405."},{"key":"e_1_3_2_1_34_1","volume-title":"Contrabert: Enhancing code pre-trained models via contrastive learning. arXiv preprint arXiv:2301.09072.","author":"Liu Shangqing","year":"2023","unstructured":"Shangqing Liu, Bozhi Wu, Xiaofei Xie, Guozhu Meng, and Yang Liu. 2023. Contrabert: Enhancing code pre-trained models via contrastive learning. arXiv preprint arXiv:2301.09072."},{"key":"e_1_3_2_1_35_1","article-title":"Graphsearchnet: Enhancing gnns via capturing global dependencies for semantic code search","author":"Liu Shangqing","year":"2023","unstructured":"Shangqing Liu, Xiaofei Xie, Jingkai Siow, Lei Ma, Guozhu Meng, and Yang Liu. 2023. Graphsearchnet: Enhancing gnns via capturing global dependencies for semantic code search. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_3_2_1_36_1","unstructured":"David Z. Morris. 2017. How Equifax Turned Its Massive Hack Into an Even Worse Dumpster Fire? http:\/\/fortune.com\/2017\/09\/09\/equifax-hack-crisis\/"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510454.3516865"},{"key":"e_1_3_2_1_39_1","unstructured":"Luis Perez and Jason Wang. 2017. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621."},{"key":"e_1_3_2_1_40_1","volume-title":"Automated Vulnerability Detection in Source Code Using Deep Representation Learning. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). 757\u2013762","author":"Russell Rebecca","year":"2018","unstructured":"Rebecca Russell, Louis Kim, Lei Hamilton, Tomo Lazovich, Jacob Harer, Onur Ozdemir, Paul Ellingwood, and Marc McConley. 2018. Automated Vulnerability Detection in Source Code Using Deep Representation Learning. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). 757\u2013762."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"e_1_3_2_1_42_1","first-page":"1","article-title":"Driller: Augmenting Fuzzing Through Selective Symbolic Execution","volume":"16","author":"Stephens Nick","year":"2016","unstructured":"Nick Stephens, John Grosen, Christopher Salls, Andrew Dutcher, Ruoyu Wang, Jacopo Corbetta, Yan Shoshitaishvili, Christopher Kruegel, and Giovanni Vigna. 2016. Driller: Augmenting Fuzzing Through Selective Symbolic Execution.. In NDSS. 16, 1\u201316.","journal-title":"NDSS."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.12"},{"key":"e_1_3_2_1_44_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998\u20136008."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSAC.2000.898880"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3044773"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.23"},{"key":"e_1_3_2_1_48_1","unstructured":"David A. Wheeler. 2017. Flawfinder. https:\/\/www.dwheeler.com\/flawfinder\/"},{"key":"e_1_3_2_1_49_1","volume-title":"29th $USENIX$ Security Symposium ($USENIX$ Security 20). 1165\u20131182.","author":"Xiao Yang","unstructured":"Yang Xiao, Bihuan Chen, Chendong Yu, Zhengzi Xu, Zimu Yuan, Feng Li, Binghong Liu, Yang Liu, Wei Huo, and Wei Zou. 2020. $MVP$: Detecting Vulnerabilities using Patch-Enhanced Vulnerability Signatures. In 29th $USENIX$ Security Symposium ($USENIX$ Security 20). 1165\u20131182."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2014.44"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2014.44"},{"key":"e_1_3_2_1_52_1","volume-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks. In Advances in Neural Information Processing Systems. 10197\u201310207.","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. 10197\u201310207."},{"key":"e_1_3_2_1_53_1","unstructured":"Terry Yue Zhuo Zhou Yang Zhensu Sun Yufei Wang Li Li Xiaoning Du Zhenchang Xing and David Lo. 2023. Data Augmentation Approaches for Source Code Models: A Survey. arXiv preprint arXiv:2305.19915."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2942930"}],"event":{"name":"LCTES '24: 25th ACM SIGPLAN\/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","location":"Copenhagen Denmark","acronym":"LCTES '24","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 25th ACM SIGPLAN\/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652032.3657564","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652032.3657564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:12Z","timestamp":1750291392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652032.3657564"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":54,"alternative-id":["10.1145\/3652032.3657564","10.1145\/3652032"],"URL":"https:\/\/doi.org\/10.1145\/3652032.3657564","relation":{},"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"2024-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}