LAN Intrusion Detection Using Convolutional Neural Networks

The world's reliance the use of the internet is growing constantly, and data are considered the most precious parameter nowadays. It is critical to keep information secure from unauthorized people and organizations. When a network is compromised, information is taken. An intrusion detection system detects both known and unexpected assaults that allow a network to be breached. In this research, we model an intrusion detection system trained to identify such attacks in LANs, and any computer network that uses data. We accomplish this by employing neural networks, a machine learning technique. We also investigate how well our model performs in multiclass categorization scenarios. On the NSL-KDD dataset, we investigate the performance of Convolutional Neural Networks such as CNN and CNN with LSTM. Our findings suggest that utilizing Convolutional Neural Networks to identify network intrusions is an effective strategy.

Automated summary

In this research, a well-trained intrusion detection system using neural networks is developed to detect attacks in LANs and other computer networks that use data. The study finds that utilizing convolutional neural networks is an effective strategy for identifying network intrusions.