Intrusion detection in SDN-IoT using robust GRU with attention mechanism and fuzzy weighting

Abstract

Dealing with the rise of complexity and increasing frequency of cyber threats in both SDN and IoT, the characteristic of intrusion detection in these platforms will be a predictable requirement to overcome the present attacks like malware, DDoS, and MITM, among others. This paper presents an all-inclusive and effective intrusion detection system that can combine advanced DL methods specifically concentrating on merging networks with LSTM and GRU. The model’s capability to identify critical information from network traffic data and use fuzzy weighting algorithms and attention mechanisms allows for correctly identifying anomalies. The system is qualified and authenticated on its effectiveness using the BoT-IoT dataset a standard for simulating authentic IoT traffic and attack patterns. Advanced optimization techniques like CGO and GBO improve the system’s computational efficiency by guaranteeing low resource consumption while preserving excellent performance. The proposed IDS has shown the capability to cruel system activities for a notable accuracy of 99.97, an F1 score of 99.94, and extremely low false-positive and false-negative rates. Such an adaptation has proven suitable for real-time SDN-IoT network operation within dynamic and resource-constrained systems with an outcome of effective and real-time mitigation of several types of threats in such atmospheres through smooth adaptability to any variation in nature of the traffic as well as diverse types of attack. An expressive upgrade over the conventional structures, this IDS is also a model for the future development in the security of networked devices.