Deep-IDS A real time intrusion detector for iot nodes using deep learning

In an era where IoT devices proliferate, the vulnerability of these nodes to network intrusions necessitates robust security measures. This study presents Deep-IDS, a real-time intrusion detection system leveraging deep learning techniques to identify and classify network intrusions. The existing system employs Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) networks for intrusion detection. The proposed system enhances detection accuracy by integrating Bidirectional Long Short-Term Memory (BiLSTM) and Feedforward Neural Networks (FNN). The front-end is developed using HTML, CSS, and JavaScript, while the back-end utilizes Python for efficient data processing and model implementation. This research aims to provide a scalable solution for safeguarding IoT networks against various intrusion types, ensuring their integrity and availability.

Keywords: IoT Security, Intrusion Detection System, Deep Learning, BiLSTM, Feedforward Neural Networks, CNN, RNN, LSTM.