The paper introduces BFLIDS, a blockchain-empowered Federated Learning-based Intrusion Detection System (IDS) designed to enhance security and intrusion detection in Internet of Medical Things (IoMT) networks. Traditional security solutions struggle with the dynamic and interconnected nature of IoMT systems, leading to critical security challenges. Machine learning (ML)-based IDS have been adopted to counter cyberattacks, but centralized ML approaches pose privacy risks due to single points of failure (SPOFs). Federated Learning (FL) is proposed as a solution, enabling model updates directly on end devices without sharing private data with a central server. BFLIDS leverages blockchain to secure transaction records, FL to maintain data privacy by training models locally, IPFS for decentralized storage, and MongoDB for efficient data management. Ethereum smart contracts oversee and secure all interactions and transactions within the system. The FedAvg algorithm is modified with Kullback–Leibler divergence estimation and adaptive weight calculation to boost model accuracy and robustness against adversarial attacks. The proposed approach uses an Adaptive Max Pooling-based Convolutional Neural Network (CNN) and a modified Bidirectional Long Short-Term Memory (BiLSTM) with attention and residual connections on Edge-IoTSet and TON-IoT datasets. The results show competitive accuracies of 97.43% (for CNNs and Edge-IoTSet), 96.02% (for BiLSTM and Edge-IoTSet), 98.21% (for CNNs and TON-IoT), and 97.42% (for BiLSTM and TON-IoT) in FL scenarios, demonstrating the effectiveness of BFLIDS in detecting intrusions and enhancing the security and privacy of IoMT networks.The paper introduces BFLIDS, a blockchain-empowered Federated Learning-based Intrusion Detection System (IDS) designed to enhance security and intrusion detection in Internet of Medical Things (IoMT) networks. Traditional security solutions struggle with the dynamic and interconnected nature of IoMT systems, leading to critical security challenges. Machine learning (ML)-based IDS have been adopted to counter cyberattacks, but centralized ML approaches pose privacy risks due to single points of failure (SPOFs). Federated Learning (FL) is proposed as a solution, enabling model updates directly on end devices without sharing private data with a central server. BFLIDS leverages blockchain to secure transaction records, FL to maintain data privacy by training models locally, IPFS for decentralized storage, and MongoDB for efficient data management. Ethereum smart contracts oversee and secure all interactions and transactions within the system. The FedAvg algorithm is modified with Kullback–Leibler divergence estimation and adaptive weight calculation to boost model accuracy and robustness against adversarial attacks. The proposed approach uses an Adaptive Max Pooling-based Convolutional Neural Network (CNN) and a modified Bidirectional Long Short-Term Memory (BiLSTM) with attention and residual connections on Edge-IoTSet and TON-IoT datasets. The results show competitive accuracies of 97.43% (for CNNs and Edge-IoTSet), 96.02% (for BiLSTM and Edge-IoTSet), 98.21% (for CNNs and TON-IoT), and 97.42% (for BiLSTM and TON-IoT) in FL scenarios, demonstrating the effectiveness of BFLIDS in detecting intrusions and enhancing the security and privacy of IoMT networks.