Advancing Security in SDN-IoT Networks: DL-Based Autonomous Anomaly Detection with Enhanced Cross-Validation for Poisoning Attack Detection

Abstract

The convergence of Software-Defined Networking (SDN) and the Internet of Things (IoT) is the emergence of highly dynamic and heterogeneous SDN-IoT networks vulnerable to various cyber threats. In response, Autonomous Anomaly Detection (AAD) systems leveraging deep learning (DL) techniques have become crucial for securing SDN-IoT networks. However, DL-based AAD systems are susceptible to adversarial attacks, particularly in continual learning settings, where models must adapt to evolving threats and changing network conditions. This paper proposes an enhanced cross-validation strategy for poisoning attack detection in DL-based AAD systems deployed in SDN-IoT networks. By integrating advanced cross-validation techniques with anomaly detection algorithms, the framework aims to maintain DL model robustness against poisoning attacks and enhance overall security. Evaluations of popular baseline datasets have provided insights into the effectiveness of detection, highlighting strengths and limitations. The discussion emphasizes the challenges and improvements in existing detection methods and contributes to advancing DL-based AAD systems for SDN-IoT networks. In addition, Future research directions aim to enhance the proposed detection mechanism and optimize scalable detection algorithms.