Design of Trustworthy Cyber–Physical–Social Systems With Discrete Bayesian Optimization

Abstract Cyber–physical–social systems (CPSS) with highly integrated functions of sensing, actuation, computation, and communication are becoming the mainstream consumer commercial products. The performance CPSS heavily relies on information sharing between devices. Given extensive data collection sharing, security privacy major concerns. Thus, one challenge designing those is how to incorporate perception trust in product design. Recently, a quantification method was proposed measure trustworthiness by quantitative metrics ability, benevolence, integrity. network architecture can be optimized choosing subnet such that maximized. combinatorial optimization problem, however, computationally challenging. Most available global algorithms for solving problems heuristic methods. In this paper, surrogate-based discrete Bayesian developed perform design, where most trustworthy respect reference node formed collaborate share with. applications ability benevolence design demonstrated.