{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automated-vulnerability-detection-in-source","title":"Automated Vulnerability Detection in Source Code Using Deep Representation Learning","arxiv_id":"1807.04320","date":"2018-07-11","proceeding":null,"authors":["Rebecca L. Russell","Louis Kim","Lei H. Hamilton","Tomo Lazovich","Jacob A. Harer","Onur Ozdemir","Paul M. Ellingwood","Marc W. McConley"],"abstract":"Increasing numbers of software vulnerabilities are discovered every year\nwhether they are reported publicly or discovered internally in proprietary\ncode. These vulnerabilities can pose serious risk of exploit and result in\nsystem compromise, information leaks, or denial of service. We leveraged the\nwealth of C and C++ open-source code available to develop a large-scale\nfunction-level vulnerability detection system using machine learning. To\nsupplement existing labeled vulnerability datasets, we compiled a vast dataset\nof millions of open-source functions and labeled it with carefully-selected\nfindings from three different static analyzers that indicate potential\nexploits. The labeled dataset is available at: https://osf.io/d45bw/. Using\nthese datasets, we developed a fast and scalable vulnerability detection tool\nbased on deep feature representation learning that directly interprets lexed\nsource code. We evaluated our tool on code from both real software packages and\nthe NIST SATE IV benchmark dataset. Our results demonstrate that deep feature\nrepresentation learning on source code is a promising approach for automated\nsoftware vulnerability detection.","url_abs":"http://arxiv.org/abs/1807.04320v2","url_pdf":"http://arxiv.org/pdf/1807.04320v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automated-vulnerability-detection-in-source","repo_url":"https://github.com/hazimhanif/svd_exp1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"automated-vulnerability-detection-in-source","repo_url":"https://github.com/hazimhanif/svd_exp3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"vulnerability-detection","task_name":"Vulnerability Detection"}],"methods":[],"datasets_introduced":[{"slug":"draper-vdisc-dataset","name":"Draper VDisc Dataset","full_name":"reza"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.04320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}