Enhancing network slice security with Deep Reinforcement Learning and Moving Target Defense strategies
Andreas Andreou, Constandinos X. Mavromoustakis, Evangelos Markakis, Athina Bourdena, George Mastorakis
Abstract
Network slicing is revolutionizing how networks are built and managed by enabling the flexible and efficient allocation of resources to meet diverse application requirements. Yet this flexibility introduces significant security challenges that must be addressed to maintain system integrity and performance. Therefore, this article presents a novel framework integrating Deep Reinforcement Learning (DRL) with Moving Target Defense (MTD) strategies to create a dynamic, multi-layered security system. By modelling the problem as a Markov Decision Process (MDP), the proposed framework leverages advanced DRL algorithms to learn optimal policies for deploying MTD mechanisms across network slices by continuously adapting defences to counter evolving cyber threats. Simulations, including comparative evaluation with baseline DRL and heuristic methods, demonstrate this integrated approach’s superiority in mitigating cyber-attacks while maintaining high network performance.