Abstract :

With The Growing Interconnection Of Technologies In Warfare Scenarios, Devices In The IoBT Have Become Integral To Modern-day Military Operations. And Yet, This Rising Interconnectivity Exposes Such Systems To Greater Cyber Threats, Particularly Malware Sophisticated Enough To Disrupt Missions Or Steal Sensitive Information. A Robust Malware Detection Solution For IoBT Devices Is Proposed In This Paper, Which Leans On Deep Eigenspace Learning To Detect Malicious Behavior At The Very Core. The System Models Software Execution From Discrimination-point Code Execution Sequencesthe Operational Code Or OpCode-as Program Behavior Into A Highly Feature-rich Vector Space. The Deep Learning Model Proposed Detects Very Small Discrepancies From Benign Software Behavior To Detect Malicious Intent And Accurately Classify Any Given Software As Either Malware Or Benign. On Top Of This, The Model Has Been Put Through Its Paces Against Common Evasion Techniques Such As Junk Code Insertion, Endowing The Model With A High Degree Of Immunity While Maintaining Performance. This Will Therefore Act As A Scalable And Smart Way To Shore Up The Cybersecurity Of Battlefield-connected Systems. Keywords : Internet Of Battlefield Things (IoBT) ,Malware Detection, Deep Learning , OpCode Analysis, Eigenspace Learning,Cybersecurity, Junk Code Insertion ,IoT Security

Published:

09-6-2025

Issue:

Vol. 25 No. 6 (2025)

Page Nos:

419-424

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite