2019/10/13 by Nof Abuzainab, Abuzainab, Nof, Erpek, Tugba +9 · 2 citations
Computer Science · Engineering · #Security in Wireless Sensor Networks #Mobile Ad Hoc Networks #Wireless Communication Security Techniques
paper · pdf · doi:10.48550/arxiv.1910.05766
The problem of quality of service (QoS) and jamming-aware communications is\nconsidered in an adversarial wireless network subject to external eavesdropping\nand jamming attacks. To ensure robust communication against jamming, an\ninterference-aware routing protocol is developed that allows nodes to avoid\ncommunication holes created by jamming attacks. Then, a distributed cooperation\nframework, based on deep reinforcement learning, is proposed that allows nodes\nto assess network conditions and make deep learning-driven, distributed, and\nreal-time decisions on whether to participate in data communications, defend\nthe network against jamming and eavesdropping attacks, or jam other\ntransmissions. The objective is to maximize the network performance that\nincorporates throughput, energy efficiency, delay, and security metrics.\nSimulation results show that the proposed jamming-aware routing approach is\nrobust against jamming and when throughput is prioritized, the proposed deep\nreinforcement learning approach can achieve significant (measured as\nthree-fold) increase in throughput, compared to a benchmark policy with fixed\nroles assigned to nodes.\n