IoT devices are everywhere sensing, collecting, storing, and computing massive amounts of data. In the Internet of Things scenario, diversified services will generate traffic with different characteristics and put forward different business requirements. The application based on network intelligent awareness plays a key role in effectively managing network and deepening the control of network. In this chapter, we propose an end-to-end IoT traffic classification method relying on a deep learning aided capsule network for the sake of forming an efficient classification mechanism that integrates feature extraction, feature selection, and classification model. Then, we propose a hybrid IDS architecture and introduce a machine learning aided detection method. In addition, we model the time-series network traffic by the recurrent neural network (RNN). The attention mechanism is introduced for assisting network traffic classification in the form of the following two models: the attention aids long short term memory (LSTM) and the hierarchical attention network (HAN). Finally, we propose to design a machine learning-based in-network Distributed Denial of Service (DDoS) detection framework. Benefit from switch processing performance, the in-network mechanism could achieve high scalability and line speed performance.