Machine Learning as the Shield: Mitigating ARP Poisoning Attacks in Software Defined Networks
Rabee Alquran, Maha Jamal, Mohammad Aljaidi, Mohammad F. Al–Jamal, Bashar Khassawneh, Ayoub Alsarhan, Omar Alidmat, Ghassan Samara, Sattam Almatarneh
Abstract
Software-defined networking (SDN) revolutionizes network management by centralizing control, but this centralization also introduces notable vulnerabilities, especially Address Resolution Protocol (ARP) poisoning attacks. These attacks exploit the ARP protocol, redirecting network traffic to malicious destinations. This research provides a deep dive into the nuances of these threats within the SDN context, outlining their mechanisms and potential countermeasures. A significant highlight of this paper is exploring Machine Learning (ML) as a pivotal mitigation approach. By analyzing and distinguishing between benign and malicious traffic patterns in real-time, ML models present a robust solution to enhance SDN security. The findings of our paper underscore the criticality of integrating these advanced predictive techniques in SDNs, paving the way for a safer and more resilient networking future.