Average consensus is essential for multi-agent systems to achieve specific functions and is widely used in network control, information fusion, etc. In conventional average consensus algorithms, all agents reach an agreement by individual calculations and sharing information with their respective neighbors. Nevertheless, the information interactions that occur in the communication network may make sensitive information be revealed. In this paper, we develop a new privacy-preserving average consensus method for unbalanced digraphs. Specifically, we ensure privacy preservation by carefully embedding randomness in mixing weights to confuse communications and introducing an extra auxiliary parameter to mask the state-updated rule in the initial several iterations. In parallel, we exploit the intrinsic robustness of consensus dynamics to guarantee that the average consensus is precisely achieved. Theoretical results demonstrate that the designed algorithms can converge linearly to the exact average consensus value and can guarantee privacy preservation of agents against both honest-but-curious and eavesdropping attacks. The designed algorithms are fundamentally different compared to differential privacy based algorithms that enable privacy preservation via sacrificing consensus performance. Finally, numerical experiments validate the correctness of the theoretical findings.

翻译：平均共识是多智能体系统实现特定功能的基础，广泛应用于网络控制、信息融合等领域。传统平均共识算法通过各智能体独立计算并与邻居共享信息来达成一致。然而，通信网络中的信息交互可能导致敏感信息泄露。本文针对非平衡有向图，提出了一种新型隐私保护平均共识方法。具体而言，我们通过精心设计混合权重中的随机性来混淆通信，并引入额外的辅助参数来掩盖初始若干次迭代中的状态更新规则，从而确保隐私保护。同时，我们利用共识动力学的内在鲁棒性来保证平均共识的精确达成。理论结果表明，所设计的算法可线性收敛至精确平均共识值，并能抵御半诚实攻击和窃听攻击，保护智能体隐私。与通过牺牲共识性能来实现隐私保护的差分隐私算法不同，本文算法具有本质区别。最后，数值实验验证了理论推导的正确性。