Intrusion Detection System in Smart Home Network Using Bidirectional LSTM and Convolutional Neural Networks Hybrid Model
This addresses security risks in IoT-enabled smart homes, but the approach is incremental as it adapts existing deep learning methods to a specific domain.
The paper tackles intrusion detection in smart home networks by proposing a hybrid model combining Bidirectional LSTM and Convolutional Neural Networks, achieving effective anomaly detection through temporal information preservation and feature extraction.
Internet of Things (IoT) allowed smart homes to improve the quality and the comfort of our daily lives. However, these conveniences introduced several security concerns that increase rapidly. IoT devices, smart home hubs, and gateway raise various security risks. The smart home gateways act as a centralized point of communication between the IoT devices, which can create a backdoor into network data for hackers. One of the common and effective ways to detect such attacks is intrusion detection in the network traffic. In this paper, we proposed an intrusion detection system (IDS) to detect anomalies in a smart home network using a bidirectional long short-term memory (BiLSTM) and convolutional neural network (CNN) hybrid model. The BiLSTM recurrent behavior provides the intrusion detection model to preserve the learned information through time, and the CNN extracts perfectly the data features. The proposed model can be applied to any smart home network gateway.