Deep Reinforcement Learning for Attacking Wireless Sensor Networks

Recent advances in Deep Reinforcement Learning allow solving increasingly complex problems. In this work, we show how current defense mechanisms in Wireless Sensor Networks are vulnerable to attacks that use these advances. We use a Deep Reinforcement Learning attacker architecture that allows having one or more attacking agents that can learn to attack using only partial observations. Then, we subject our architecture to a test-bench consisting of two defense mechanisms against a distributed spectrum sensing attack and a backoff attack. Our simulations show that our attacker learns to exploit these systems without having a priori information about the defense mechanism used nor its concrete parameters. Since our attacker requires minimal hyper-parameter tuning, scales with the number of attackers, and learns only by interacting with the defense mechanism, it poses a significant threat to current defense procedures.

Distributed Spectrum Management in Cognitive Radio Networks by Consensus-Based Reinforcement Learning

In this paper, we propose a new algorithm for distributed spectrum sensing and channel selection in cognitive radio networks based on consensus. The algorithm operates within a multi-agent reinforcement learning scheme. The proposed consensus strategy, implemented over a directed, typically sparse, time-varying low-bandwidth communication network, enforces collaboration between the agents in a completely decentralized and distributed way. The motivation for the proposed approach comes directly from typical cognitive radio networks’ practical scenarios, where such a decentralized setting and distributed operation is of essential importance. Specifically, the proposed setting provides all the agents, in unknown environmental and application conditions, with viable network-wide information. Hence, a set of participating agents becomes capable of successful calculation of the optimal joint spectrum sensing and channel selection strategy even if the individual agents are not. The proposed algorithm is, by its nature, scalable and robust to node and link failures. The paper presents a detailed discussion and analysis of the algorithm’s characteristics, including the effects of denoising, the possibility of organizing coordinated actions, and the convergence rate improvement induced by the consensus scheme. The results of extensive simulations demonstrate the high effectiveness of the proposed algorithm, and that its behavior is close to the centralized scheme even in the case of sparse neighbor-based inter-node communication.

Cooperative Fusion Architecture-based Distributed Spectrum Sensing Under Rayleigh Fading Channel

Cognitive radio (CR) is one of the most promising technology soon due to the scarcity of the spectrum, especially at microwave band. CR faces massive resistance from the industry because of the potential interference caused by the secondary users. Spectrum sensing forms an important functionality for CR systems. However, such detection performance is usually compromised by shadowing and fading channel conditions. Cooperative sensing is one of the crucial solutions to overcome degraded detection performance. To improve the sensing performance and reduce the reporting error, a distributed architecture for processing and fusion of sensing information is proposed in this work. In dense network scenarios, the decision fusion for cooperated users could be complex and reported sensing traffic may require large bandwidth. This paper proposes a new distributed detection and adapted threshold based on controlled false alarm probability to improve sensing reliability and efficiency in a highly Rayleigh faded environment. A distributed detection is developed by selecting fusion nodes (FN) that are dynamically selected from a group of nodes. The detection threshold is calculated adaptively using the link quality indicator (LQI) of the sensing channel. Moreover, the proposed method can significantly minimize the typically transmitted bits in the reporting channel. The paper also discussed in detail the design parameter of the CR number on the performance of fusion values. The simulation analysis shows that the performance of the distributed cooperative sensing (DCS) process is considerably improved by the adapted threshold. The numerical results demonstrated that the error was remarkably minimized. The ROC curve of the sensing process is notably improved for detection probability and false alarm probability, respectively. Finally, it was shown that the requirement of sensitivity can be greatly improved up to 0.95.