eISSN: 3087-4262 editor@aimjournals.com
All Journals
Submit your article

International Journal of Intelligent Data and Machine Learning

Open Access Peer Review International
Open Access

Identification of Harmful Programs Using a Fusion of Deep Feature Extraction Networks and Context-Aware Sequential Modeling Techniques

DOI
PDF
Dr. Alexei V. Morozov 1 , Dr. Elena S. Petrova 1 ,
4 Department of Data Science and Computational Analytics Moscow Institute of Technology and Data Systems Moscow, Russia
4 School of Artificial Intelligence and Big Data Saint Petersburg National Research University Saint Petersburg, Russia

Abstract

The proliferation of malicious software across digital ecosystems has necessitated the development of advanced detection mechanisms capable of identifying increasingly sophisticated threats. Traditional signature-based approaches have proven inadequate in addressing polymorphic and zero-day attacks, thereby driving the adoption of machine learning and deep learning methodologies in cybersecurity. This study investigates a hybrid framework for the identification of harmful programs through the integration of deep feature extraction networks and context-aware sequential modeling techniques.

The research synthesizes theoretical foundations from neural network-based classification, autoencoder-driven representation learning, and sequence modeling approaches such as recurrent neural networks and transformer architectures. By leveraging deep feature extraction mechanisms, the framework captures high-dimensional representations of executable patterns, while context-aware sequential modeling enhances the system’s ability to interpret temporal and structural dependencies within code and behavioral data.

The study adopts a conceptual-analytical methodology grounded in recent advancements in malware detection, intrusion prevention, and adversarial resilience. The integration of hybrid models enables improved classification accuracy, particularly in environments characterized by dynamic threat evolution. Furthermore, the framework incorporates feature selection, anomaly detection, and optimization strategies to enhance computational efficiency and scalability.

Findings suggest that the fusion of convolutional neural architectures, autoencoder-based encoding, and sequential learning models significantly improves detection performance compared to standalone approaches. The hybrid model demonstrates enhanced capability in identifying obfuscated malware, ransomware variants, and network-based intrusion patterns. However, challenges related to model interpretability, data heterogeneity, and adversarial manipulation remain critical concerns.

This research contributes to the cybersecurity domain by proposing a unified modeling paradigm that aligns deep feature extraction with contextual sequence learning. The study provides theoretical and practical insights for developing robust, adaptive, and scalable malware detection systems, thereby supporting the advancement of intelligent cybersecurity frameworks.

Keywords

Malware Detection, Deep Learning, Feature Extraction, Sequential Modeling

References

📄 R. Beg, R. K. Pateriya, and D. S. Tomar, “Design of an iterative method for malware detection using autoencoders and hybrid machine learning models,” IEEE Access, vol. PP, no. 99, p. 1, Jan. 2024.
📄 S. A. Ebiaredoh-Mienye, E. Esenogho, and T. G. Swart, “Integrating enhanced sparse autoencoder-based artificial neural network technique and softmax regression for medical diagnosis,” Electronics, vol. 9, no. 11, 1963, Nov. 2020.
📄 M. Esnaashari and N. Moradi, “Predicting vulnerability to malware using machine learning models: A study on Microsoft Windows machines,” arXiv (Cornell University), Jan. 2025.
📄 K. Gupta, N. Jiwani, M. Haris, R. Datta, and N. Afreen, “A neural network approach for malware classification,” in Proc. 2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Nov. 2022.
📄 R. Islam, M. I. Sayed, S. Saha, M. J. Hossain, and M. A. Masud, “Android malware classification using optimum feature selection and ensemble machine learning,” Internet of Things and Cyber-Physical Systems, vol. 3, pp. 100–111, 2023.
📄 J. Kipongo, T. G. Swart, and E. Esenogho, “Artificial intelligence-based intrusion detection and prevention in edge-assisted SDWSN with modified honeycomb structure,” IEEE Access, vol. 12, pp. 3140–3175, 2024.
📄 F. Manavi and A. Hamzeh, “A novel approach for ransomware detection based on PE header using graph embedding,” Journal of Computer Virology and Hacking Techniques, Jan. 2022.
📄 S. Okdem and S. Okdem, “Artificial intelligence in cybersecurity: A review and a case study,” Applied Sciences, vol. 14, no. 22, 10487, 2024.
📄 M. T. Signes-Pont, A. Cortés-Castillo, H. Mora-Mora, and J. Szymanski, “Modelling the malware propagation in mobile computer devices,” Computers & Security, vol. 79, pp. 80–93, Nov. 2018.
📄 B. Singh and S. S. Cheema. (2024). emerging trends in AI-powered malware detection: A review of real-time and adversarially resilient techniques. Propulsiontechjournal.com. [Online]. Available: https://www.propulsiontechjournal.com/index.php/journal/article/view/8411/5281
📄 S. Wasoye, M. Stevens, C. Morgan, D. Hughes, and J. Walker, “Ransomware classification using BTLS algorithm and machine learning approaches,” Research Square (Research Square), Sep. 2024.
📄 X. Xing, X. Jin, H. Elahi, H. Jiang, and G. Wang, “A malware detection approach using autoencoder in deep learning,” IEEE Access, vol. 10, pp. 25696–25706, 2022.
📄 Y. Xue, C. Kang, and H. Yu, “HAE-HRL: A network intrusion detection system utilizing a novel autoencoder and a hybrid enhanced LSTM-CNN-based residual network,” Computers & Security, vol. 151, 104328, Apr. 2025.
📄 Κ. Γιαπαντζής, “XLCNN: Pre-trained transformer model for malware detection,” Lib.uom.gr, 2020.

Similar Articles

21-30 of 38

You may also start an advanced similarity search for this article.