https://iaeme.com/Home/journal/IJCET 3243 editor@iaeme.com International Journal of Computer Engineering and Technology (IJCET) Volume 16, Issue 1, Jan-Feb 2025, pp. 3243-3259, Article ID: IJCET_16_01_226 Available online at https://iaeme.com/Home/issue/IJCET?Volume=16&Issue=1 ISSN Print: 0976-6367; ISSN Online: 0976-6375; Journal ID: 5751-5249 Impact Factor (2025): 18.59 (Based on Google Scholar Citation) DOI: https://doi.org/10.34218/IJCET_16_01_226 © IAEME Publication A SMART THREAT DETECTION MODEL FOR COMPLEX ROUTING NETWORKS USING AI- BASED RECURRENT NEURAL NETWORKS Vivek Lakshman Bhargav Sunkara University of South Florida, USA. ABSTRACT Today’s modern routing networks have become inherently complex and interconnected by nature. These traits make them vulnerable to a wide range of cyber threats. Traditional rule-based systems alone can no longer detect and defend these evolving threats, as manual monitoring cannot keep up with the complexity. This paper introduces a smart threat detection model utilizing Artificial Intelligence (AI), specifically Recurrent Neural Networks (RNNs) to provide real-time threat detection. The detection model analyzes a network features such as traffic patterns, device settings, configurations, and NetFlow logs to establish and understand the network's normal behavior and detect anomalies at a granular level. RNNs are best suited for this approach as they can learn and interpret the context of alerts over time. This model also incorporates adaptive algorithms that can adjust detection thresholds and rules based on real-time network behavior. This behavior ensures continuous adaptation to new threats while minimizing false positives. The results from experiments on real-world routing networks presented in this paper justify the model’s scalability and effectiveness in improving detection performance.