The rapid development of Internet of Things (IoT) devices has significantly increased network attacks and cyber threats, necessitating robust and efficient Intrusion Detection Systems (IDS). Traditional IDS approaches often struggle with the unique challenges posed by IoT environments, such as data privacy concerns, device heterogeneity, and limited computational resources. This talk will focus on the innovative use of Federated Machine Learning (FML) to enhance intrusion detection in IoT environments. FML mitigates data privacy risks while maintaining the ability to learn from a diverse range of data sources using decentralised model training approach. Highlighting the potential of FML as a solution to strengthen IDS effectiveness against evolving cyber threats, along with other real-world applications in IoT networks.