Next Article in Journal
Diffusion-Guided Model Predictive Control for Signal Temporal Logic Specifications
Previous Article in Journal
Topology Robustness of State Estimation Against False Data Injection and Network Parameter Attacks on Power Monitoring and Control Systems
Previous Article in Special Issue
An Efficient Certificate-Based Linearly Homomorphic Signature Scheme for Secure Network Coding
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 15
Issue 3
10.3390/electronics15030552
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Cyber Attack Path Prediction Approach Based on aText-Enhanced Graph Attention Mechanism

by
Hanjun Gao
1,
Hang Tong
1,
Baoyan Yong
2 and
Gang Shen
2,3,4,*
1
China Nuclear Power Operation Technology Corporation, Ltd. (CNPO), Wuhan 430074, China
2
School of Computer Science and Artificial Intelligence, Hubei University of Technology, Wuhan 430068, China
3
Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network, Wuhan 430068, China
4
Hubei Provincial Engineering Research Center for Digital & Intelligent Manufacturing Technologies and Applications, Wuhan 430068, China
*
Author to whom correspondence should be addressed.
Electronics 2026, 15(3), 552; https://doi.org/10.3390/electronics15030552
Submission received: 31 December 2025 / Revised: 24 January 2026 / Accepted: 25 January 2026 / Published: 27 January 2026
(This article belongs to the Special Issue Cryptography in Internet of Things)
Review Reports Versions Notes

Abstract

In order to solve the problem of traditional methods not being able to discover hidden attack trajectories, we propose a cyber attack path prediction approach based on a text-enhanced graph attention mechanism in this paper. Specifically, we design an ontology that captures multi-dimensional links between vulnerabilities, weaknesses, attack patterns, and tactics by integrating CVE, CWE, CAPEC, and ATT&CK into Neo4j. Then, we inject natural language descriptions into the attention mechanism to develop a text-enhanced GAT that can alleviate data sparsity. The experiment shows that compared with existing baselines, our approach improveds MRR and Hits@5 by 12.3% and 13.2%, respectively. Therefore, the proposed approach can accurately predict attack paths and support active cyber defense.
Keywords: knowledge graph; IoT; attack path prediction; ontological models; data fusion knowledge graph; IoT; attack path prediction; ontological models; data fusion

Share and Cite

MDPI and ACS Style

Gao, H.; Tong, H.; Yong, B.; Shen, G. A Cyber Attack Path Prediction Approach Based on aText-Enhanced Graph Attention Mechanism. Electronics 2026, 15, 552. https://doi.org/10.3390/electronics15030552

AMA Style

Gao H, Tong H, Yong B, Shen G. A Cyber Attack Path Prediction Approach Based on aText-Enhanced Graph Attention Mechanism. Electronics. 2026; 15(3):552. https://doi.org/10.3390/electronics15030552

Chicago/Turabian Style

Gao, Hanjun, Hang Tong, Baoyan Yong, and Gang Shen. 2026. "A Cyber Attack Path Prediction Approach Based on aText-Enhanced Graph Attention Mechanism" Electronics 15, no. 3: 552. https://doi.org/10.3390/electronics15030552

APA Style

Gao, H., Tong, H., Yong, B., & Shen, G. (2026). A Cyber Attack Path Prediction Approach Based on aText-Enhanced Graph Attention Mechanism. Electronics, 15(3), 552. https://doi.org/10.3390/electronics15030552

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop