Q-learning Based Optimal False Data Injection Attack on Probabilistic Boolean Control Networks
This addresses security vulnerabilities in control systems for domains like cybersecurity, but it is incremental as it builds on existing Q-learning methods.
The paper tackles the problem of optimal false data injection attacks on probabilistic Boolean control networks when the attacker lacks system model knowledge, using a Q-learning algorithm and an improved version that handles large-scale networks, achieving effective attack strategies as verified on 10-node and 28-node networks.
In this paper, we present a reinforcement learning (RL) method for solving optimal false data injection attack problems in probabilistic Boolean control networks (PBCNs) where the attacker lacks knowledge of the system model. Specifically, we employ a Q-learning (QL) algorithm to address this problem. We then propose an improved QL algorithm that not only enhances learning efficiency but also obtains optimal attack strategies for large-scale PBCNs that the standard QL algorithm cannot handle. Finally, we verify the effectiveness of our proposed approach by considering two attacked PBCNs, including a 10-node network and a 28-node network.