WASP-NEST-AIR2
Abstract
The Cloud-Edge Continuum (CEC) is a fundamental and essential component of future information infrastructure. Technologies such as IoT, 5G, and real-time applications rely on CEC as the underlying architecture to deliver low-latency services. However, CEC is highly susceptible to cyber threats, among which Distributed Denial of Service (DDoS) attacks are particularly disruptive. These attacks not only compromise the availability of time-sensitive services but also degrade the performance of computing support algorithms. A key challenge in DDoS detection within the CEC environment lies in achieving a balance between high detection accuracy and efficient model training. Ensuring timely service delivery while maintaining robust detection performance remains a critical issue. This project aims to develop machine learning (ML) and deep learning (DL) algorithms for detecting DDoS attacks in CEC environments. The research will leverage both public datasets and specialized datasets generated through testbed experiments. The objectives of this project are threefold: 1) Develop an effective detection model tailored for DDoS attacks in CEC, ensuring high detection performance. 2) Optimize model inference and training time to enable real-time detection, facilitating rapid mitigation strategies. 3) Investigate the model’s domain adaptability to enhance its generalization across diverse attack scenarios and datasets.
By addressing these challenges, this research aims to contribute to the advancement of secure, efficient, and adaptive DDoS detection mechanisms for next-generation cloud-edge computing environments.
