Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le, Triet H. M., Babar, M. Ali
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911966717542400
author Le, Triet H. M.
Babar, M. Ali
author_facet Le, Triet H. M.
Babar, M. Ali
contents Background: Software Vulnerability (SV) prediction needs large-sized and high-quality data to perform well. Current SV datasets mostly require expensive labeling efforts by experts (human-labeled) and thus are limited in size. Meanwhile, there are growing efforts in automatic SV labeling at scale. However, the fitness of auto-labeled data for SV prediction is still largely unknown. Aims: We quantitatively and qualitatively study the quality and use of the state-of-the-art auto-labeled SV data, D2A, for SV prediction. Method: Using multiple sources and manual validation, we curate clean SV data from human-labeled SV-fixing commits in two well-known projects for investigating the auto-labeled counterparts. Results: We discover that 50+% of the auto-labeled SVs are noisy (incorrectly labeled), and they hardly overlap with the publicly reported ones. Yet, SV prediction models utilizing the noisy auto-labeled SVs can perform up to 22% and 90% better in Matthews Correlation Coefficient and Recall, respectively, than the original models. We also reveal the promises and difficulties of applying noise-reduction methods for automatically addressing the noise in auto-labeled SV data to maximize the data utilization for SV prediction. Conclusions: Our study informs the benefits and challenges of using auto-labeled SVs, paving the way for large-scale SV prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?
Le, Triet H. M.
Babar, M. Ali
Software Engineering
Cryptography and Security
Machine Learning
Background: Software Vulnerability (SV) prediction needs large-sized and high-quality data to perform well. Current SV datasets mostly require expensive labeling efforts by experts (human-labeled) and thus are limited in size. Meanwhile, there are growing efforts in automatic SV labeling at scale. However, the fitness of auto-labeled data for SV prediction is still largely unknown. Aims: We quantitatively and qualitatively study the quality and use of the state-of-the-art auto-labeled SV data, D2A, for SV prediction. Method: Using multiple sources and manual validation, we curate clean SV data from human-labeled SV-fixing commits in two well-known projects for investigating the auto-labeled counterparts. Results: We discover that 50+% of the auto-labeled SVs are noisy (incorrectly labeled), and they hardly overlap with the publicly reported ones. Yet, SV prediction models utilizing the noisy auto-labeled SVs can perform up to 22% and 90% better in Matthews Correlation Coefficient and Recall, respectively, than the original models. We also reveal the promises and difficulties of applying noise-reduction methods for automatically addressing the noise in auto-labeled SV data to maximize the data utilization for SV prediction. Conclusions: Our study informs the benefits and challenges of using auto-labeled SVs, paving the way for large-scale SV prediction.
title Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?
topic Software Engineering
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2407.17803