IJWMT Vol. 15, No. 4, 8 Aug. 2025
Cover page and Table of Contents: PDF (size: 399KB)
PDF (399KB), PP.65-72
Views: 0 Downloads: 0
Artificial Intelligence, Cybersecurity, Anomaly Detection, Autoencoder, Network Traffic Analysis, Machine Learning, Intrusion Detection, Data Protection, Deep Learning, Threat Detection
The escalating complexity of cybersecurity threats necessitates advanced technological solutions to protect digital infrastructures. This study explores the application of Autoencoder neural networks, a deep learning model, for anomaly detection in network traffic, aiming to enhance real-time identification of cyberattacks. Using the CICIDS2017 dataset, which encompasses diverse attack types such as Distributed Denial of Service (DDoS) and infiltration, the Autoencoder was trained to detect deviations from normal traffic patterns based on reconstruction errors. The model was optimized through preprocessing, feature selection, and hyperparameter tuning, achieving strong performance metrics including precision, recall, F1-score, accuracy, and ROC-AUC. Despite its effectiveness in distinguishing normal and malicious traffic, challenges arose in detecting stealthy attacks like slow brute-force attempts. These results underscore the Autoencoder's potential in cybersecurity frameworks and highlight opportunities for improvement through adaptive thresholds and hybrid models. This study contributes to advancing AI-driven anomaly detection, promoting proactive defense against evolving cyber threats.
Iryna Zavushchak, "The Impact of Artificial Intelligence on Cybersecurity and Data Protection", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.15, No.4, pp. 65-72, 2025. DOI:10.5815/ijwmt.2025.04.05
[1]I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016. DOI: 10.5555/3086952.
[2]M. Cicirello, and M. Pontani. “Deep Learning in Cybersecurity: A Review.” Journal of Network Security, vol. 32, no. 4, pp. 124–135, 2019. DOI: 10.1016/j.jns.2019.07.006.
[3]Canadian Institute for Cybersecurity. “CICIDS2017 Dataset.” University of New Brunswick. Available online: https://www.unb.ca/cic/datasets/ids-2017.html (accessed Oct. 10, 2024).
[4]M. Abou-Elhamayed, S. J. Hussain, F. Al-Turjman, and O. K. Ewees. “Anomaly Detection in Network Traffic Using Autoencoders.” IEEE Transactions on Cybersecurity, vol. 17, no. 2, pp. 67–78, 2021. DOI: 10.1109/TCS.2021.3053349.
[5]K. Ahmed, A. Shahid, F. Usman, and M. Zahid. “AI-Driven Cybersecurity Frameworks: An Overview.” ACM Computing Surveys, vol. 55, no. 3, pp. 1–29, 2023. DOI: 10.1145/3543879.
[6]N. Papernot, P. McDaniel, I. Goodfellow, S. Jha, Z. Celik, and A. Swami. “Practical Black-Box Attacks Against Machine Learning.” Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security (ASIACCS), pp. 506–519, 2017. DOI: 10.1145/3052973.3053009.
[7]A. Roy, S. Sharma, A. Bose, and A. Mukherjee. “Towards Robust Anomaly Detection: Adversarial Training for Autoencoders.” Information Sciences, vol. 602, pp. 150–170, 2022. DOI: 10.1016/j.ins.2022.04.016.
[8]I. Zavushchak, Z. Rybchak. “AI-Powered Tools for Data Privacy Enhancement in Cybersecurity Systems.” Cybersecurity and Privacy Journal, vol. 11, no. 1, pp. 35–47, 2022. DOI: 10.1016/j.cybsec.2022.01.004.
[9]I. Zavushchak, Z. Rybchak, and P. Dovganych. “Anomaly Detection in IoT Networks Using Autoencoders: A Comparative Study.” International Journal of Computer Science and Network Security, vol. 20, no. 12, pp. 45–55, 2023. DOI: 10.22937/IJCSNS.2023.012.