FedCTI: Federated Learning and Cyber Threat Intelligence on the Edge for secure IoT Networks

The Abstract

The rapid increase in the number of Internet of Things (IoT) has brought numerous benefits and conveniences, but it has also introduced significant cybersecurity challenges. IoT devices are often connected to networks and to the internet, making them potential targets for cyberattacks (e.g., Mirai attack). As the IoT ecosystem grows, there’s a pressing need to enhance cybersecurity measures to ensure the protection of these interconnected devices and the data they handle. On the other hand, Cyber Threat Intelligence (CTI) involves the collection, analysis, and distribution of information about potential and ongoing cyber threats. CTI helps organizations understand the threat landscape and take proactive measures to mitigate risks. In the context of IoT, having timely and accurate CTI is crucial for identifying emerging threats and vulnerabilities. While sharing CTI knowledge is important, doing so in a distributed IoT environment presents challenges. The data generated and collected by IoT devices can be sensitive and private, making it essential to find ways to share CTI knowledge without compromising data privacy. This research focuses on leveraging Federated Learning (FL) techniques to facilitate secure and privacy-preserving CTI knowledge sharing in IoT networks by proposing a solution called FedCTI. This paper explores the potential benefits, architecture, experiments, and challenges associated with using FL for sharing CTI knowledge to secure IoT systems.

Keywords

Attacks; Cyber Threat Intelligence; Cybersecurity; Defense; Federated learning; IoT; Knowledge; Mitigation; Threats

Recommended citation: El Jaouhari, Saad and Etiabi, Yaya, "FedCTI: Federated Learning and Cyber Threat Intelligence on the Edge for secure IoT Networks," Proceedings of the 13th International Conference on the Internet of Things, pp. 98 – 104, 2023.