Development of an Intelligent Detection Framework for Trojan Horse Malware

Amidst an escalating digital arms race, the burgeoning complexity of Trojan horse architecture has neutralized the efficacy of conventional signature-reliant defense paradigms. This research pioneers a high-fidelity Intelligent Detection Framework designed to transcend static identification by leveraging the predictive power of ensemble learning. Our experimental architecture utilized a curated corpus of 4,000 observations, maintaining a strict equilibrium between malicious Trojan payloads and benign system processes. The operational pipeline transformed raw telemetry into a refined feature space through a sequence of one-hot encoding, Min-max scaling, and rigorous Principal Component Analysis (PCA). By distilling the input data into the 20 most significant behavioral dimensions, the framework mitigated computational latency while amplifying signal clarity. Performance benchmarks revealed a stark divergence between the evaluated heuristics: while the Decision Tree (DT) model offered baseline competence, the Extreme Gradient Boosting (XGBoost) configuration attained a dominant 98.7% accuracy and a 99.2% recall. This near-absolute sensitivity is pivotal, as it virtually eliminates the "blind spots" typically exploited by zero-day mutations. By fusing behavioral telemetry with high-performance gradient boosting, this study establishes a scalable blueprint for fortifying endpoint security against the next generation of stealth-oriented cyber threats.

Malware Heuristics, XGBoost, Computational Dimensionality, PCA

1. Ab Razak, M. F., Anuar, N. B., Othman, F., Firdaus, A., Afifi, F., & Salam, S. (2022). Trojan horse detection using machine learning algorithms. Journal of Cybersecurity and Privacy, 2(1), 12–28. [Google Scholar] [Crossref]

2. Abualhaj, M. M., Al-Khasawneh, A., & Al-Zubi, S. (2024). Memory-based Trojan detection using decision tree classifiers. Computers & Security, 138, 103-115. [Google Scholar] [Crossref]

3. Ahuja, R., & Salunke, S. (2025). Hybrid machine learning and blockchain framework for enhanced threat detection. International Journal of Information Security, 24(2), 45–62. [Google Scholar] [Crossref]

4. Azeem, M., Khan, M. A., & Tariq, M. (2024). Comparative analysis of machine learning classifiers for malware classification. IEEE Access, 12, 14210–14225. [Google Scholar] [Crossref]

5. Chen, X., Li, S., & Zhang, Y. (2019). The evolution of zero-day attacks and the inadequacy of signature-based detection. Journal of Network Security, 15(3), 210–225. [Google Scholar] [Crossref]

6. Kamboj, S., Singh, J., & Kumar, R. (2023). Multi-malware detection using file-based feature extraction and machine learning. Cybersecurity and Intelligence, 6(1), 88–104. [Google Scholar] [Crossref]

7. Kumar, P., Singh, S., & Varma, A. (2024). Ensemble learning for malware detection: A study on Random Forest and XGBoost. Advanced Computing Reports, 9(4), 56–72. [Google Scholar] [Crossref]

8. MergeGuard. (2025). Post-training mitigation strategies for Trojan attacks on neural networks.Technical Whitepaper. [Google Scholar] [Crossref]

9. Öztürk, M., & Hızal, S. (2024). Evaluation of machine learning models on the CIC-MalMem-2022 dataset for obfuscated malware detection. Data Science and Cybersecurity Review, 11(2), 34–49. [Google Scholar] [Crossref]

10. Saxe, J., Berlin, K., & Saunders, R. (2015). eXpose: A character-level convolutional neural network with embeddings for detecting malicious URLs, file paths and registry keys. arXiv preprint arXiv:1702.08568. [Google Scholar] [Crossref]

11. Singh, A., Jain, R., & Kapoor, S. (2019). Advanced evasion techniques in modern malware: A survey. Security and Communication Networks, 2019, 1–18. [Google Scholar] [Crossref]

12. Singh, R., Patel, D., & Sharma, V. (2025). Bypassing AI-based malware detectors through API-call manipulation. Journal of Forensic Informatics, 13(1), 12–29. [Google Scholar] [Crossref]

13. Song, J., Xu, T., & Wu, L. (2025). Deep learning for malware detection: A 72-study systematic literature review. Journal of Big Data, 12(1), 45–70. [Google Scholar] [Crossref]

14. Song, J., Xu, T., & Wu, L. (2025). Feature extraction and deep learning trends in malware detection. Neurocomputing Survey, 31(2), 112–135. [Google Scholar] [Crossref]

15. T-Miner. (2021). Generative model defense against Trojan triggers in natural language processing. Proceedings of the Security and Privacy Symposium. [Google Scholar] [Crossref]

16. Talukder, M. A., & Talukder, S. (2025). Exploratory data analysis and machine learning for dynamic Trojan detection. International Journal of Computer Science & Engineering, 14(3), 201–215. [Google Scholar] [Crossref]

17. Tanikonda, S., Roberts, M., & Lee, K. (2025). The shift toward AI-driven (AID) malware: Autonomously bypassing security paradigms. Cyber Resilience Quarterly, 7(2), 101–118. [Google Scholar] [Crossref]

18. Wang, H., Zhang, F., & Liu, P. (2020). Taxonomies of malware and their propagation vectors in modern networks. Computing Surveys, 53(4), 1–35. [Google Scholar] [Crossref]

• The Impact of Ownership Structure on Dividend Payout Policy of Listed Plantation Companies in Sri Lanka
• Urban Sustainability in North-East India: A Study through the lens of NER-SDG index
• Performance Assessment of Predictive Forecasting Techniques for Enhancing Hospital Supply Chain Efficiency in Healthcare Logistics
• The Fractured Self in Julian Barnes' Postmodern Fiction: Identity Crisis and Deflation in Metroland and the Sense of an Ending
• Impact of Flood on the Employment, Labour Productivity and Migration of Agricultural Labour in North Bihar