Security of Spectrum Learning in Cognitive Radios
This addresses security concerns for cognitive radio systems, which are crucial for efficient spectrum usage, but the work appears incremental as it focuses on improving existing methods rather than introducing a new paradigm.
The paper tackles the vulnerability of reinforcement learning-based channel selection algorithms in cognitive radios to belief manipulation attacks, proposing mitigation techniques to enhance their robustness.
Due to delay and energy constraints, a cognitive radio may not be able to perform spectrum sensing in all available channels. Therefore, a sensing policy is needed to decide which channels to sense. The channel selection problem is the problem of designing such a sensing policy to maximize throughput while avoiding interference to primary users. The channel selection problem can be formulated as a reinforcement learning problem. Channel selection schemes that employ reinforcement machine learning algorithms are vulnerable to belief manipulation attacks that contaminate the knowledge base of the learning algorithms. In this paper, we analyze the security of channel selection algorithms that are based on reinforcement learning and propose mitigation techniques that make these algorithms more robust against belief manipulation attacks.