RSL: Representative Sample Learning

With the development of Industrial Internet of Things (IIoT) technology, an increasing number of ICS (Industrial Control System) devices are connecting to the company's traditional information network, making it convenient for users to access them remotely and for overall planning. However, this exposes industrial control systems to the internet, making them vulnerable to cyberattacks. In this scenario, it is necessary to analyze the traffic of industrial control systems and prevent unknown attacks. We have generated additional samples from representative samples to increase the number of training samples, thereby improving the accuracy of anomaly detection.