Black-hole (BH) attacks are among the most critical security threats in Mobile Ad Hoc Networks (MANETs) due to their decentralized and highly dynamic nature. Existing protection mechanisms primarily rely on threshold-based monitoring, trust evaluation, and route observation techniques, which often suffer from limited packet information, poor scalability, and inadequate attack verification capabilities. To address these limitations, this paper proposes a centralized federated framework for black-hole attack detection in MANETs. The proposed framework integrates Linear Scaling-based Shark Smell Optimization Algorithm (LS-SSOA) for Cluster Head (CH) selection, Gini Canberra Spearman-based K-Means Algorithm (GCS-KMA) for clustering, Round Log Sum BCrypt-based Message Authentication Code (RLBC-MAC) for secure route authorization, and Judy-Verkle Tree (JVT) for malicious path verification. A federated learning architecture consisting of a global server and local models is employed to continuously monitor network activities and improve attack detection efficiency. Experimental evaluation was conducted using MANET networks comprising 50–250 nodes in a Python-based simulation environment. The proposed framework achieved a detection accuracy of 98.96%, a false prediction rate of 2.06%, throughput of 6445 kbps, and reduced computational overhead compared with existing methods. The results demonstrate that the proposed centralized federated framework significantly improves network security, route reliability, and attack detection performance in MANET environments.

The Internet of Things (IoT) is an ever-expanding network that links all objects to the web so that they can communicate with one another using standardized protocols. Recently, IoT networks have been extensively used in advanced applications like smart factories, smart homes, smart grids, smart cities, etc. They can be used in conjunction with artificial intelligence (AI) and machine learning to facilitate a data collection procedure that is both simplified and more dynamic. Along with the services provided by IoT applications, various security issues are also raised. The accessing of IoT devices is mainly through an untrusted network like the Internet which makes them unprotected against a wide range of malicious attacks. The detection performance of current IDSs is hindered by issues including false alarms, low detection rate, an unbalanced dataset, and slow response time. This study proposes a new intrusion detection system (IDS) for the IoT that utilizes the chaotic improved Black Widow Optimization Kernel Extreme Learning Machine (CIBWO-KELM) algorithm to address these problems. Initially, the pre-processing of the dataset is carried out using min-max normalization, changing string values to numerical values and changing IP address to numerical values. The selection of the highest performing feature set is achieved through the information gain method (IGM), and finally, the intrusion detection is performed by the CIBWO-KELM algorithm. Python is the tool utilized for testing, while the BoT-IoT dataset is used for simulation analysis. The suggested model achieves an accuracy level of 99.7% when applied to the BoT-IoT dataset. In addition, the results of the studies demonstrate that the proposed model outperforms other current techniques.