The use of IPv6 routing protocol in low power lossy network (RPL) for IoT-based networks has become a standard practice. Despite its benefits, RPL is vulnerable to routing attacks that can compromise the network's performance. Various efforts have been made to secure IoT networks, but most of these solutions have failed to provide adequate protection, since they have been generally evaluated in limited settings. To address this issue, this project proposes the use of coevolutionary computation techniques to develop an intrusion detection model that can accurately detect attacks in harsh network environments. The coevolutionary approach has several advantages. First, it allows for the creation of a more realistic and challenging network environment that accurately reflects the conditions of real-world networks. Second, it enables the intrusion detection system to learn and adapt to changing network conditions, which is critical for effective attack detection.