Socialbots are intelligent software that controls all behaviour of fake accounts in an online social network. Since they are armed with detection evasion techniques, it is valuable to be able to determine the effectiveness of these techniques. In this study, an analytical model is developed to estimate a lower bound for the cost of automatic establishment of a socialbot network. Moreover, by considering fake accounts purchasing as an establishment strategy, an upper bound is suggested for acceptable costs. These two boundaries are compared to decide on the economic feasibility of a socialbot network design strategy. To demonstrate the practicality and effectiveness of the model, two case studies are investigated. They show that although designing a fully stealthy socialbot network is economically feasible, the infiltration time would be unacceptable. Thus, this ideal situation in which the establishment is fully stealthy, performs in a tolerable time, and satisfactory infiltration scale, is impractical. A possible solution could be achieved by reducing the time and cost in exchange for less stealthy behaviour while the infiltration scale kept unchanged. Since the model presents a trade-off between stealthiness, time, and cost, it is a useful tool facilitating the design of a possible strategy.

中文翻译：

---

建立隐身社交机器人网络的经济可行性研究

Socialbots是一款智能软件，可控制在线社交网络中假账户的所有行为。由于他们配备了逃避检测技术，因此能够确定这些技术的有效性非常有价值。在这项研究中，开发了一种分析模型来估计自动建立社交机器人网络的成本的下限。此外，通过将虚假帐户购买作为建立策略，建议了可接受费用的上限。将这两个边界进行比较，以决定socialbot网络设计策略的经济可行性。为了证明该模型的实用性和有效性，研究了两个案例研究。他们表明，尽管设计一个完全隐身的socialbot网络在经济上是可行的，渗透时间将是不可接受的。因此，这种理想的情况是不切实际的，在该理想情况下，设施是完全隐身的，可以在可容忍的时间内运行，并且具有令人满意的渗透规模。一个可能的解决方案可以通过减少时间和成本来换取较少的隐身行为，而渗透规模保持不变来实现。由于该模型在隐身性，时间和成本之间进行了折衷，因此它是有助于设计可能策略的有用工具。