John M. Acken¹ and Naresh K. Sehgal², ¹Portland State University, USA, ²Data Centre Group, Intel Corp, USA

Present state of edge computing is an environment of different computing capabilities connecting via a wide variety of communication paths. This situation creates both great operational capability opportunities and unimaginable security problems. This paper emphasizes that the traditional approaches to security of identifying a security threat and developing the technology and policies to defend against that threat are no longer adequate. The wide variety of security levels, computational capabilities, and communication channels requires a learning, responsive, varied, and individualized approach to information security. We describe a classification of the nature of transactions with respect to security based upon relationships, history, trust status, requested actions and resulting response choices. Problem is that the trust evaluation has to be individualized between each pair of devices participating in edge computing. We propose that each element in the edge computing world utilizes a localized ability to establish an adaptive learning trust model with each entity that communicates with the element. Specifically, the model we propose increments or decrements the value of trust score based upon each interaction.

Edge Computing, Security, Adaptive learning, Trust model, Threats, Cloud Computing, Information Security