A Feed-Forward and Back Propagation Neural Network Approach for Identifying Network Anomalies

The internet’s ability to link all of our gadgets together has a profound impact on our daily routines. Numerous industries, including medicine, smart buildings, and commerce, all make use of network-based technologies. These programmers cater to big populations and offer a wide variety of services. As a result, the security of network-based applications has continuously attracted attention from academics and business leaders. Thanks to deep learning’s development, we can now probe previously inaccessible topics. Hackers take advantage of security holes in networks to access protected resources. This kind of knowledge and access to systems can do irreparable harm and inflict incalculable losses. Therefore, it is crucial that these network attacks be uncovered. While systematically probing every conceivable set of network features, the few inputs required by deep learning-based algorithms are a major selling point. In light of this, in this research, we provide a deep learning architecture based on feed-forward back propagation neural networks for the purpose of detecting anomalies into a network. Our investigation uncovered 14 unique forms of malicious network activity. The studies were conducted using the standard-setting CICIDS2017 dataset, and the findings show an accuracy of 91.02%.