Saved in:
Bibliographic Details
Main Authors: Nong, Yu, Fang, Richard, Yi, Guangbei, Zhao, Kunsong, Luo, Xiapu, Chen, Feng, Cai, Haipeng
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.15436
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914630503235584
author Nong, Yu
Fang, Richard
Yi, Guangbei
Zhao, Kunsong
Luo, Xiapu
Chen, Feng
Cai, Haipeng
author_facet Nong, Yu
Fang, Richard
Yi, Guangbei
Zhao, Kunsong
Luo, Xiapu
Chen, Feng
Cai, Haipeng
contents Accompanying the successes of learning-based defensive software vulnerability analyses is the lack of large and quality sets of labeled vulnerable program samples, which impedes further advancement of those defenses. Existing automated sample generation approaches have shown potentials yet still fall short of practical expectations due to the high noise in the generated samples. This paper proposes VGX, a new technique aimed for large-scale generation of high-quality vulnerability datasets. Given a normal program, VGX identifies the code contexts in which vulnerabilities can be injected, using a customized Transformer featured with a new value-flowbased position encoding and pre-trained against new objectives particularly for learning code structure and context. Then, VGX materializes vulnerability-injection code editing in the identified contexts using patterns of such edits obtained from both historical fixes and human knowledge about real-world vulnerabilities. Compared to four state-of-the-art (SOTA) baselines (pattern-, Transformer-, GNN-, and pattern+Transformer-based), VGX achieved 99.09-890.06% higher F1 and 22.45%-328.47% higher label accuracy. For in-the-wild sample production, VGX generated 150,392 vulnerable samples, from which we randomly chose 10% to assess how much these samples help vulnerability detection, localization, and repair. Our results show SOTA techniques for these three application tasks achieved 19.15-330.80% higher F1, 12.86-19.31% higher top-10 accuracy, and 85.02-99.30% higher top-50 accuracy, respectively, by adding those samples to their original training data. These samples also helped a SOTA vulnerability detector discover 13 more real-world vulnerabilities (CVEs) in critical systems (e.g., Linux kernel) that would be missed by the original model.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15436
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses
Nong, Yu
Fang, Richard
Yi, Guangbei
Zhao, Kunsong
Luo, Xiapu
Chen, Feng
Cai, Haipeng
Software Engineering
Accompanying the successes of learning-based defensive software vulnerability analyses is the lack of large and quality sets of labeled vulnerable program samples, which impedes further advancement of those defenses. Existing automated sample generation approaches have shown potentials yet still fall short of practical expectations due to the high noise in the generated samples. This paper proposes VGX, a new technique aimed for large-scale generation of high-quality vulnerability datasets. Given a normal program, VGX identifies the code contexts in which vulnerabilities can be injected, using a customized Transformer featured with a new value-flowbased position encoding and pre-trained against new objectives particularly for learning code structure and context. Then, VGX materializes vulnerability-injection code editing in the identified contexts using patterns of such edits obtained from both historical fixes and human knowledge about real-world vulnerabilities. Compared to four state-of-the-art (SOTA) baselines (pattern-, Transformer-, GNN-, and pattern+Transformer-based), VGX achieved 99.09-890.06% higher F1 and 22.45%-328.47% higher label accuracy. For in-the-wild sample production, VGX generated 150,392 vulnerable samples, from which we randomly chose 10% to assess how much these samples help vulnerability detection, localization, and repair. Our results show SOTA techniques for these three application tasks achieved 19.15-330.80% higher F1, 12.86-19.31% higher top-10 accuracy, and 85.02-99.30% higher top-50 accuracy, respectively, by adding those samples to their original training data. These samples also helped a SOTA vulnerability detector discover 13 more real-world vulnerabilities (CVEs) in critical systems (e.g., Linux kernel) that would be missed by the original model.
title VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses
topic Software Engineering
url https://arxiv.org/abs/2310.15436