SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
2 results
Search Results
Item Restricted Lightweight ML-Based Drone Intrusion Detection System Through Model Compression(University of North Texas, 2025) Alruwaili, Fawaz Juhayyim M; Cihan, TuncThe adoption of drones in diverse domains (e.g., surveillance, agriculture, and disaster management), together with their integration of advanced technologies and dependence on wireless communication, has significantly increased the need to secure drone networks against cyber threats. Traditional network-based intrusion detection systems (NIDS) can be insufficient against novel or adaptive cyber threats and exceed the computational limits of drones. Thus, we need lightweight and efficient drone-specific NIDS solutions. This dissertation addresses this concern with the goal of achieving an effective balance between security, efficiency, and model accuracy without significantly compromising detection performance. Hence, two complementary main contributions are proposed: First, a lightweight ML-based NIDS optimized for individual drones, utilizing a quantized deep neural network (DNN) through post-training quantization (PTQ), enabling real-time, on-board intrusion detection. Second, a framework for swarm-based deployments that leverage federated learning and knowledge distillation to enable distributed training and lightweight model deployment while preserving data privacy and minimizing communication overhead. Both contributions were evaluated using real-world drone network datasets. The first contribution achieved 95.03% accuracy with significantly reduced model size and inference latency, making it suit- able for real-time and onboard deployment. The second contribution was deployed using Raspberry Pi 4 devices and demonstrated improved accuracy, convergence, and communication efficiency, achieving up to 76% reduction in communication overhead and 29% lower CPU usage. The results demonstrate the practicality and effectiveness of the proposed solutions in meeting the unique demands of both individual and swarm-based drone deployments, while achieving a robust balance between security and efficiency.14 0Item Restricted Moving Target Detection and Prediction towards Cyber Agile Cellular Networks(Alotaibi, Saad, 2019-04-29) Alotaibi, Saad; Song, HoubingAgile networks such as cellular networks are often prone to attacks emanating from various loopholes. The security loopholes increase the vulnerability of a network whereby the attackers are able to utilize the attack surface to execute an attack. One of the best approach of eliminating the security loopholes is to reduce the attack surface that in the network. An approach known as Moving Target Defense (MTD) is a robust mechanism aimed at reducing the attack surface in a cyber-agile network. This paper proposes the development of an MTD framework aimed at reducing the attack surface in a cloud- based network. The approach aims to formulate how multiple virtual machines can be migrated from one network layer to another with the aim of minimizing the chances of an attacker exploiting the network vulnerabilities. The proposed framework also addresses the mechanism of transforming the I.P addresses of the virtual machines after successful migration to the new network layer. The framework is simulated with the OpenStack platform whereby the network layer is implemented using nova- compute while the hardware is implemented using neuron framework. The algorithmic framework is further supported and implemented using Python programming platform. The experimental results indicate that the migration process is attained within a maximum duration of 0.3 seconds, which is adequate enough to prevent an attacker from executing an attack on the network. The proposed MTD framework is capable of improving the security of a cyber-agile network by minimizing the attack surface. For enhancing the security of the system, the IP mutation methodology has also been proposed along with MTD. For checking the efficiency of proposed IP mutation methodology, two metrics were defined i.e. assurance and avoidance. The results for IP mutation methodology suggested that it uses flexible and elastic characteristics of SDN and helps to enhance the security of the system.14 0