Innovating Network Security: Federated Transfer Learning for Intrusion Detection

Le résumé fourni par la source

Due to the dynamic nature of threats in cyberspace, there is need for sophisticated IDS that can offer online and adaptant security solutions to various network structures. For this purpose, this paper suggests a new approach that uses federated transfer learning to improve threat detection and response. FTL combines both the global and local model, where by the autonomous systems can learn from others while at the same time the data belonging to each system remains protected. Hence, the approach used in our work focuses on improving the overall IDS scalability, as well as its flexibility and productivity in large and distributed environments. Through the use of federated learning, it signifies a stronger and harder to penetrate defense system and has a faster reaction time once a threat is identified. This paper discusses possible implementations of the threat recognition security system herein presented with a view of demonstrating its usefulness in the contemporary interconnected world. The proposed system is a break through in the current network security system and proffers a strong solution to the new development in the network security.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.