A Survey on Trusted Distributed Artificial Intelligence

Abstract

Emerging Artificial Intelligence (AI) systems are revolutionizing computing and data processing approaches with their strong impact on society. Data is processed with automated labelling pipelines rather than providing it as input to the system. The innovative nature increases the overall performance of monitoring/detection/reaction mechanisms for efficient system resource management. However, due to hardware-driven design limitations, networking and trust mechanisms are not flexible and adaptive enough to be able to interact and control the resources dynamically. Novel adaptive software-driven design approaches can enable us to build growing intelligent mechanisms with software-defined networking (SDN) features by virtualizing network functionalities with maximized features. These challenges and critical feature sets have been identified and introduced into this survey with their scientific background for AI systems and growing intelligent mechanisms. Furthermore, obstacles and research challenges between 1950-2021 are explored and discussed with a focus on recent years. The challenges are categorized according to three defined architectural perspectives (central, decentral/autonomous, distributed/hybrid) for emerging trusted distributed AI mechanisms. Therefore, resiliency and robustness can be assured in a dynamic context with an end-to-end Trusted Execution Environment (TEE) for growing intelligent mechanisms and systems. Furthermore, as presented in the paper, the trust measurement, quantification, and justification methodologies on top of Trusted Distributed AI (TDAI) can be applied in emerging distributed systems and their underlying diverse application domains, which will be explored and experimented in our future related works.