This paper presents a novel intrusion detection system (IDS) for wireless ad hoc networks using graph neural networks (GNNs). The system is designed to efficiently detect malicious packets in dynamic and resource-constrained environments. The proposed GNN-based IDS is placed at zone heads and is optimized for feature engineering and normalization to ensure efficient performance. Evaluation on the NSL-KDD dataset shows that the GNN-based IDS outperforms traditional models like CNNs and Transformers, demonstrating its adaptability to dynamic network environments. The system excels in understanding complex dependencies, contributing to efficient intrusion detection and network security in resource-constrained wireless ad hoc networks. The paper emphasizes the resource efficiency of the GNN-based approach, making it practical for real-time intrusion detection in such networks. The study highlights the transformative role of GNNs in enhancing wireless ad hoc network security and contributes to discussions on efficient intrusion detection, offering innovative solutions against emerging threats. Traditional intrusion detection systems (IDS) are ill-suited for wireless ad hoc networks due to their static nature and inability to adapt to dynamic environments. Conventional systems rely on predefined rules and static signatures, which are ineffective in detecting novel and evolving threats. Machine learning-based IDS systems, while more adaptive, still face challenges in scalability and real-time performance. This paper introduces a pioneering approach using GNNs to create a resource-efficient IDS for wireless ad hoc networks. The proposed system is compared with other deep learning technologies, including CNNs and Transformers, through extensive experimentation on specialized datasets. The results show that the GNN-based IDS is superior in terms of resource efficiency, ability to detect novel threats, and adaptability to evolving attack strategies. The study underscores the potential of GNNs in creating efficient IDS solutions and highlights the need for innovative approaches to address the evolving threat landscape.This paper presents a novel intrusion detection system (IDS) for wireless ad hoc networks using graph neural networks (GNNs). The system is designed to efficiently detect malicious packets in dynamic and resource-constrained environments. The proposed GNN-based IDS is placed at zone heads and is optimized for feature engineering and normalization to ensure efficient performance. Evaluation on the NSL-KDD dataset shows that the GNN-based IDS outperforms traditional models like CNNs and Transformers, demonstrating its adaptability to dynamic network environments. The system excels in understanding complex dependencies, contributing to efficient intrusion detection and network security in resource-constrained wireless ad hoc networks. The paper emphasizes the resource efficiency of the GNN-based approach, making it practical for real-time intrusion detection in such networks. The study highlights the transformative role of GNNs in enhancing wireless ad hoc network security and contributes to discussions on efficient intrusion detection, offering innovative solutions against emerging threats. Traditional intrusion detection systems (IDS) are ill-suited for wireless ad hoc networks due to their static nature and inability to adapt to dynamic environments. Conventional systems rely on predefined rules and static signatures, which are ineffective in detecting novel and evolving threats. Machine learning-based IDS systems, while more adaptive, still face challenges in scalability and real-time performance. This paper introduces a pioneering approach using GNNs to create a resource-efficient IDS for wireless ad hoc networks. The proposed system is compared with other deep learning technologies, including CNNs and Transformers, through extensive experimentation on specialized datasets. The results show that the GNN-based IDS is superior in terms of resource efficiency, ability to detect novel threats, and adaptability to evolving attack strategies. The study underscores the potential of GNNs in creating efficient IDS solutions and highlights the need for innovative approaches to address the evolving threat landscape.