Next-generation intrusion Detection performs an essential task in modern cyberspace to differentiate between normal and abnormal network traffic in incoming and outgoing network packets. This is one of industrial control systems’ most important security solutions to detect potential attacks like ransomware, DDoS, etc. Financial institutions are persistent targets of DDoS attacks that disrupt the services, and IDS can detect these attacks by monitoring abnormal traffic. Therefore, this research focuses on enhancing IDS performance by combining Active Learning with Artificial Neural Networks (ANN). We have implemented and compared two models, ANN with Active Learning and ANN without Active Learning. The experimental results show that Active learning with ANN consumes fewer resources and performs better than ANN without Active learning with an accuracy of 99%.