Federated Swarm Intelligence for Adversarial Threat Mitigation through Self-Healing Anomaly Consensus Networks

Mission-critical networks (MCNs) increasingly depend on distributed intelligence for intrusion detection but remain susceptible to adversarial threats and poisoned feedback. As cyber-physical systems scale, ensuring secure and adaptive anomaly detection across heterogeneous, edge-centric environments is vital. Centralized approaches suffer from latency and single points of failure, while conventional federated learning lacks trust and poisoning resilience. These gaps expose MCNs to inference inconsistencies, delayed mitigation, and adversarial manipulation under real-time constraints. This paper presents a federated swarm intelligence framework for secure anomaly detection and adversarial resilience in MCNs. The system integrates a hybrid global-local anomaly detection model, composed of an autoencoder and an isolation forest with a reputation-based belief propagation protocol. Each node performs local inference and shares Indicators of Compromise (IOCs) with trusted peers. Trust scores are dynamically updated using a similarity-weighted belief function, allowing the swarm to isolate poisoned nodes and maintain robust consensus. A self-healing loop filters malicious contributions from global model updates, ensuring continuous adaptation to threat evolution. Experimental results across TON_IoT, CICIDS2017, and UNSW-NB15 datasets demonstrate improved detection accuracy, reduced false positives, and resilience against up to 30% adversarial node participation. This work establishes a scalable defense paradigm for edge-intelligent, real-time MCN environments.