×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerSoftware Defined Wireless Sensor Networks (SDWSN) has emerged as a contemporary model to achieve dynamic and secure control in the realm of Internet of Things (IoT) applications. By leveraging the benefits of Software Defined Networks (SDN), SDWSN enables ease of management and configuration of wireless networks, thereby overcoming the challenges associated with traditional Wireless Sensor Networks (WSN). However, SDWSN networks are susceptible to emerging network intrusion and threats, particularly Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks, which can significantly impact the network’s performance and cause operational losses. This study proposes a machine learning based algorithm for detecting and preventing DoS and DDoS attacks in SDWSN networks. The proposed algorithm uses various features to distinguish between benign traffic and malicious traffic generated by attacks. The results demonstrate that the proposed algorithm can effectively detect and prevent DoS attacks, significantly contributing to the security of SDWSN networks.
The reliance on networks and systems has grown rapidly in contemporary times, leading to increased vulnerability to cyber assaults. The Distributed Denial-of-Service (Distributed Denial of Service) attack, a threat that can cause great financial liabilities and reputation damage. To address this problem, Machine Learning (ML) algorithms have gained huge attention, enabling the detection and prevention of DDOS (Distributed Denial of Service) Attacks. In this study, we proposed a novel security mechanism to avoid Distributed Denial of Service attacks. Using an ensemble learning methodology aims to it also can differentiate between normal network traffic and the malicious flood of Distributed Denial of Service attack traffic. The study also evaluates the performance of two well-known ML algorithms, namely, the decision tree and random forest, which were used to execute the proposed method. Tree in defending against Distributed Denial of Service (DDoS) attacks. We test the models using a publicly available dataset called TIME SERIES DATASET FOR DISTRIBUTED DENIAL OF SERVICE ATTACK DETECTION. We compare the performance of models using a list of evaluation metrics developing the Model. This step involves fetching the data, preprocessing it, and splitting it into training and testing subgroups, model selection, and validation. When applied to a database of nearly 11,000 time series; in some cases, the proposed approach manifested promising results and reached an Accuracy (ACC) of up to 100 % in the dataset. Ultimately, this proposed method detects and mitigates distributed denial of service. The solution to securing communication systems from this increasing cyber threat is this: preventing attacks from being successful.