在线学习的主用户仿冒攻击策略

在认知无线网络中,次用户通过频谱感知来学习频谱环境,从而接入那些没有被主用户占用的频谱空隙。事实上,多种恶意攻击的存在会影响次用户频谱感知的可靠性。只有深入研究恶意攻击策略,才能确保认知无线网络的安全。基于此,研究了一种认知无线网络中的欺骗性干扰策略,即主用户仿冒攻击策略,该攻击策略通过在信道上传输伪造的主用户信号来降低次用户频谱感知的性能。具体来说,将攻击策略问题建模为在线学习问题,并提出基于汤普森采样的攻击策略以实现在探索不确定信道和利用高性能信道间的权衡。仿真结果表明,与现有的攻击策略相比,提出的攻击策略能更好地通过在线学习优化攻击决策以适应非平稳的认知无线网络。

Online learning for primary user emulation attack strategy

Spectrum sensing is one of the main components of cognitive radio (CR) system, where the secondary users (SUs) are endowed the ability of sensing and learning radio spectrum environment to get the spectrum holes that the primary users (PUs) do not occupy. However, spectrum sensing is not absolutely secure. The existence of various malicious attacks can seriously affect the reliability and effectiveness of spectrum sensing. Based on this, we study a spoofing jamming strategy in cognitive wireless network, called as primary user emulation attack strategy, which transmits forged primary user signals over channels to deteriorate the spectrum sensing performance of the secondary users. More concretely, we model the attack strategy as an online learning problem based on the non-stationary characteristics of the spectrum environment and secondary user behavior in cognitive wireless network, and propose a Thompson sampling based attack strategy. The simulation results show that compared with the existing attack strategy, the proposed attack strategy can better adapt to the non-stationary cognitive wireless network by optimizing the attack decision through online learning.