Abstract

The rapid expansion of Internet of Things (IoT) ecosystems has significantly increased the complexity and scale of cyber forensic investigations, necessitating innovative and efficient analytical methods. This study proposes an Optimized Deep Neuro-Fuzzy Network (DNFN) framework designed to enhance forensic capabilities in IoT-driven big data environments. The framework synergizes the feature extraction strengths of deep learning with the interpretative advantages of fuzzy logic, while employing optimization algorithms to fine-tune its parameters for improved performance. The DNFN framework addresses key challenges such as data heterogeneity, dynamic threat landscapes, and resource constraints in IoT ecosystems. Extensive experimentation on benchmark datasets demonstrates the framework's ability to achieve high accuracy in detecting cyber anomalies, reduce false positive rates, and support comprehensive forensic analysis. The proposed approach is a significant step toward enabling scalable, interpretable, and robust cyber forensic solutions tailored for the evolving complexities of IoT-driven networks.

Keywords:

Optimized Deep Neuro-Fuzzy Networks, IoT Cyber Forensics, Big Data Analysis, Cybersecurity, Forensic Investigation, IoT Ecosystems, Anomaly Detection, Artificial Intelligence, Fuzzy Logic, Deep Learning, Optimization Techniques, Cyber Threat Analysis, Scalable Forensic Solutions.

References:

1) Buczak, A. L., & Guven, E. (2016). A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials, 18(2), 1153-1176.

2) Rashid, M., Kamruzzaman, J., Hassan, M. M., & Alam, F. (2020). A survey on cyber security issues in IoT and their mitigation techniques: Recent advances and challenges. Journal of Network and Computer Applications, 164, 102693.

3) Shafiq, M., Gu, Z., Liu, X., & Yue, H. (2020). Anomalous activity detection in IoT network using fuzzy logic-based machine learning technique. IEEE Access, 8, 182459-182472.

4) IoT-23 Dataset. (2020). A labeled dataset with benign and malicious IoT network traffic. Stratosphere Laboratory, Czech Technical University in Prague.

5) Moustafa, N., & Slay, J. (2015). UNSW-NB15: A comprehensive dataset for network intrusion detection systems (UNSW-NB15 network data set). Military Communications and Information Systems Conference (MilCIS), Canberra, Australia, 2015.

6) Ravi, V., & Ravi, S. (2015). A survey on deep learning models in cyber security. Journal of Information Security and Applications, 22, 27-40.

7) Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338-353.

8) Kennedy, J., & Eberhart, R. (1995). Particle swarm optimization. Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia, 1995, pp. 1942-1948.

9) Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer.

10) Gupta, B. B., Agrawal, D. P., & Yamaguchi, S. (2016). Handbook of research on modern cryptographic solutions for computer and cyber security. IGI Global.