Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection

<p dir="ltr">Data package for "Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection", published in ICSE 2024, with updates from Artifact Evaluation.</p><p dir="ltr">Paper link: <a href="https://www.computer.org/csdl/proceedings-article/icse/2024/021700a166/1RLIWqviwEM" rel="nofollow" target="_blank">https://www.computer.org/csdl/proceedings-article/icse/2024/021700a166/1RLIWqviwEM</a></p><p dir="ltr">See Github repo for updates: <a href="https://github.com/ISU-PAAL/DeepDFA" rel="noreferrer" target="_blank">https://github.com/ISU-PAAL/DeepDFA</a></p><p dir="ltr">Data dictionary:</p><ul><li>before.zip: CFGs of Big-Vul dataset, generated by Joern.</li><li>preprocessed_data.zip: preprocessed data from Big-Vul for running DeepDFA, including preprocessed Joern CFGs and abstract dataflow embeddings.</li><li>DeepDFA-code.zip: most recent version of the code as of the publication of this artifact, see Github repo for updates: <a href="https://github.com/ISU-PAAL/DeepDFA" rel="noreferrer" target="_blank">https://github.com/ISU-PAAL/DeepDFA</a></li><li>MSR_data_cleaned.csv: original Big-Vul dataset, see original source: <a href="https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset" rel="noreferrer" target="_blank">https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset</a></li><li>MSR_LineVul: LineVul's preprocessed version of the Big-Vul dataset, see original source: <a href="https://github.com/awsm-research/LineVul" rel="noreferrer" target="_blank">https://github.com/awsm-research/LineVul</a></li></ul><p dir="ltr">Changelog:</p><ul><li>v1 2023-09-20: original data package and Github repo published.</li><li>v2 2024-01-04: added full instructions and bug fixes for Artifact Evaluation.</li><li>v3 2024-01-10: integrated feedback from Artifact Evaluation.</li></ul><p></p>