In this paper, two reputation based algorithms called Reputation and audit based clustering (RAC) algorithm and Reputation and audit based clustering with auxiliary anchor node (RACA) algorithm are proposed to defend against Byzantine attacks in distributed detection networks when the fusion center (FC) has no prior knowledge of the attacking strategy of Byzantine nodes. By updating the reputation index of the sensors in cluster-based networks, the system can accurately identify Byzantine nodes. The simulation results show that both proposed algorithms have superior detection performance compared with other algorithms. The proposed RACA algorithm works well even when the number of Byzantine nodes exceeds half of the total number of sensors in the network. Furthermore, the robustness of our proposed algorithms is evaluated in a dynamically changing scenario, where the attacking parameters change over time. We show that our algorithms can still achieve superior detection performance.

翻译：在本文中,建议使用两种基于声誉的算法,即光学和审计的集群算法和与辅助锚节节算法(RACA)基于声誉的组合和审计的组合法,以便在聚集中心事先对拜占庭节点的攻击战略没有了解时,在分布式探测网络中防范拜占庭攻击攻击。通过更新集束网络传感器的声誉指数,该系统可以准确地识别Byzantine节点。模拟结果表明,拟议的两种算法与其他算法相比,均具有较高的探测性能。拟议的RACA算法即使在拜占庭节点的数目超过网络中传感器总数的一半的情况下,仍然运作良好。此外,我们提议的算法的稳健性是在一个动态变化的情景中评估的,攻击参数随着时间的变化而变化。我们表明,我们的算法仍然能够达到较高的探测性能。