Advancing Intrusion Detection: Application of Distributed Deep Learning on the KDD Cup 99 Dataset

Abstract

Intrusion Detection Systems (IDS) are crucial for protecting IT infrastructures against increasingly sophisticated and evolving threats. Faced with complex attacks such as stealthy or polymorphic threats, conventional methods based on rules or signatures show their limitations. An innovative IDS approach utilizing a deep neural network integrated into a distributed architecture for dynamic and precise network traffic analysis is introduced. Tested on the KDD Cup 99 dataset, this method demonstrated an accuracy of 99.90%, a recall of 99.89%, and a specificity of 100%, marking a significant improvement over traditional IDS systems. The exceptional performance obtained encourages the broader adoption of this system and suggests significant potential for revolutionizing IT security practices. The implications of the findings for current security strategies are also discussed, and directions for future research are proposed.