English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, deep learning (DL)-based methods have been widely used incode vulnerability detection. The DL-based methods typically extract structuralinformation from source code, e.g., code structure graph, and adopt neuralnetworks such as Graph Neural Networks (GNNs) to learn the graphrepresentations. However, these methods fail to consider the heterogeneousrelations in the code structure graph, i.e., the heterogeneous relations meanthat the different types of edges connect different types of nodes in thegraph, which may obstruct the graph representation learning. Besides, thesemethods are limited in capturing long-range dependencies due to the deep levelsin the code structure graph. In this paper, we propose a Meta-path basedAttentional Graph learning model for code vulNErability deTection, calledMAGNET. MAGNET constructs a multi-granularity meta-path graph for each codesnippet, in which the heterogeneous relations are denoted as meta-paths torepresent the structural information. A meta-path based hierarchicalattentional graph neural network is also proposed to capture the relationsbetween distant nodes in the graph. We evaluate MAGNET on three public datasetsand the results show that MAGNET outperforms the best baseline method in termsof F1 score by 6.32%, 21.50%, and 25.40%, respectively. MAGNET also achievesthe best performance among all the baseline methods in detecting Top-25 mostdangerous Common Weakness Enumerations (CWEs), further demonstrating itseffectiveness in vulnerability detection.

Meta-Path Based Attentional Graph Learning Model for Vulnerability Detection