Dual-Reinforcement-Learning-Based Attack Path Prediction for 5G Industrial Cyber–Physical Systems
Xinge Li, Xiaoya Hu, Tao Jiang
Abstract
5G industrial cyber–physical systems (5G-ICPSs) have attracted substantial research interests due to their capability in the interconnection of everything. However, integrating the 5G network may expose systems to more potential risks. To reveal attack propagation, an attack path prediction approach based on dual reinforcement learning (RL) is proposed. First, a dual-network model is established, incorporating the security constraints for attacks against the 5G network into the attack graph. Second, employing RL, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q $ </tex-math></inline-formula> -value updating functions and reward mechanisms based on topology and vulnerability are designed. Finally, an optimal attack path prediction algorithm is developed. Unlike traditional methods, the proposed approach does not rely on the monotonicity assumption that a system component has only one vulnerability, enabling it to accurately predict the optimal attack paths. Our simulation results demonstrate that the proposed approach can identify possible attack sources and paths from a 5G-ICPS.