The Internet of Things (IoT) is rapid growth in the current era of globalization, especially the IoT network which is the main target of cyber attacks. One of the
attacks that occur on the IoT Network is a traffic attack. Traffic attack is an attack on excessive network traffic that aims to disrupt or paralyze a system. The excessive
traffic is typically in the form of malware attacking IoT networks, is distributed Denial of Service (DDoS), Denial of Service (DoS), Recon, Web-based, Brute Force, and Spoofing or deliberately injected by malicious individuals or organizations.
To counteract this traffic, one solution is to use an attack detection system, known as Intrusion Detection System (IDS). IDS is a model for analyzing and detecting attacks on traffic in IoT networks. This attack detection system can use the Convolutional Neural Networks (CNN) algorithm. In detecting traffic in IDS in IoT, the CNN algorithm can be used to predict the possibility of attack by utilizing patterns and features contained in networks traffic. So, Deep Learning such as the
CNN algorithm can detect attack in traffic appropriately and is suitable for attack detection on IoT networks.
The scenario result of this research can simulated and evaluated the system created. As a result, performance tests using the CNN Algorithm can produce model
80% accuracy. The classification results for F1-Score 82.0%, Precision 86.8%, Recall 80.2%, and processing time to evaluate or detection time is 29.54 second.