VIDA : Enhancing Vulnerability Detection and Impact Analysis via Diffusion‐Guided Heterogeneous Knowledge Aggregation
Software: Practice and Experience · 2026-12 · 56 (12) · 1435-1448
DOI: 10.1002/spe.70095 ↗Kurz gefasst
Fachartikel in der Zeitschrift Software: Practice and Experience, online erschienen am 29.07.2026. Verfasst von Ying Xing und 7 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.
Abstract (Originalsprache)
Background
Detecting software vulnerabilities and analyzing their impacts on interconnected software components are crucial to ensuring the security of software‐driven edge computing and Artificial Intelligence of Things (AIoT) systems, especially with the growing prevalence of software supply chain attacks. Knowledge graphs (KGs) have been used to model complex semantic dependencies between vulnerabilities and software components. However, existing KGs often contain noisy or irrelevant relations, which significantly hinder their utility in downstream tasks.
Objective
This study aims to improve vulnerability detection and impact analysis by denoising vulnerability KGs and generating task‐oriented vulnerability representations.
Methods
We propose a diffusion‐based graph learning framework for denoising vulnerability KGs. The framework first employs a diffusion process to reconstruct relational structures within the KG, guided by a graph alignment mechanism that integrates collaborative signals from the software component–vulnerability bipartite graph. This alignment encourages the denoised KG to preserve relations most relevant to downstream tasks. Subsequently, a heterogeneous information network aggregates multi‐relational information from the denoised KG to produce knowledge‐enhanced embeddings for vulnerabilities.
Results
Through this two‐stage learning paradigm, the framework effectively captures both semantic and relational dependencies among heterogeneous entities and generates task‐oriented representations for vulnerability detection and impact analysis. Experimental results on a widely used benchmark demonstrate that the framework can effectively identify latent relationships between vulnerabilities and software components and predict high‐risk vulnerabilities.
Conclusion
The proposed framework improves the utility of vulnerability KGs by suppressing noisy relations and preserving task‐relevant information, providing practical insights for proactive vulnerability mitigation and patch recommendation.
Zitieren
APA
Xing, Y., Liu, Z., Xing, Y., Song, C., Yang, B., Yang, Y., Zhang, Y., & Zhao, H. (2026). VIDA : Enhancing Vulnerability Detection and Impact Analysis via Diffusion‐Guided Heterogeneous Knowledge Aggregation. Software: Practice and Experience, 56(12), 1435-1448. https://doi.org/10.1002/spe.70095
Vancouver
Xing Y, Liu Z, Xing Y, Song C, Yang B, Yang Y, et al. VIDA : Enhancing Vulnerability Detection and Impact Analysis via Diffusion‐Guided Heterogeneous Knowledge Aggregation. Software: Practice and Experience. 2026;56(12):1435-1448. doi:10.1002/spe.70095
BibTeX
@article{Xing2026,
author = {Xing, Ying and Liu, Zujun and Xing, Yonghao and Song, Chengyu and Yang, Bin and Yang, Yun and Zhang, Yuwei and Zhao, Hua},
title = {VIDA : Enhancing Vulnerability Detection and Impact Analysis via Diffusion‐Guided Heterogeneous Knowledge Aggregation},
journal = {Software: Practice and Experience},
year = {2026},
volume = {56},
number = {12},
pages = {1435--1448},
doi = {10.1002/spe.70095}
}
EUVIMED