Malicious Attacks and Defenses for Deep-Reinforcement-Learning-Based Dynamic Spectrum Access

Dynamic spectrum access (DSA) is a technology proposed to address issues, such as spectrum scarcity, inflexible spectrum management, and spectrum waste in wireless communication. This is crucial in supporting the escalating demands of spectrum particularly for Internet of Things (IoT)-based applications. Modeling the spectrum access problem as a Markov decision process (MDP) and incorporating deep reinforcement learning (DRL) have emerged as a cutting-edge approach to tackle this challenge. However, the application of DRL in spectrum access is vulnerability to malicious attacks, posing significant security threats. We introduce both glass-box adversarial attack and closed-box jamming attack over-the-air to assess the susceptibility of DRL-based spectrum access system. The simulation results demonstrate the destructive effect of these attack methods in disrupting the spectrum access process of DRL models, adversely affecting the overall performance of communication systems. Moreover, we propose effective defense mechanisms to mitigate potential threats posed by adversary on DRL-based spectrum access. By incorporating advanced defense mechanisms, we successfully enhance the robustness of the system, ensuring the secure and stable operation of the spectrum access system.