The classification of cyber threat detection is found to be one of the emerging areas in computer vision. The main goal is to improve the accuracy of the classification of cyber threat detection. The principle of conventional IDS is to detect attempts to attack a network and to identify abnormal activities and behaviors. The reasons, including the uncertainty in searching for types of attacks and the increasing complexity of advanced cyber-attacks, IDS calls for the need for integration of methods such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) more precisely Long Short Term Memory (LSTM). In this work, CNN and RNN are employed for the development of discriminative characteristics and sequential-labels respectively. The CNN and RNN learn input traffic data in sync with a gradually increasing granularity such that both spatial and temporal features of the data can be effectively extracted. A convolutional recurrent neural network is used to create a deep learning based hybrid ID framework that predicts and classifies malicious cyber-attacks in the network. To assess the efficacy of the HCRNN proposed method, experiments were done on publicly available Intrusion Detection data, specifically the NSLKDD dataset. The experiments prove that the proposed HCRNN substantially outperforms current ID methodologies attaining high malicious attack detection rate accuracy.