Exploiting Blockchain to Make AI Trustworthy: A Software Development Lifecycle View

Artificial intelligence (AI) is a very powerful technology and can be a potential disrupter and essential enabler. As AI expands into almost every aspect of our lives, people raise serious concerns about AI misbehaving and misuse. To address this concern, international organizations have put forward ethics guidelines for constructing trustworthy AI (TAI), including privacy, transparency, fairness, robustness, accountability, and so on. However, because of the black-box characteristics and complex models of AI systems, it is challenging to translate these guiding principles and aspirations into AI systems. Blockchain, an important decentralized technology, can provide the capabilities of transparency, traceability, immutability, and secure sharing and hence can be used to make AI trustworthy. In this paper, we survey studies on blockchain-based TAI (BTAI) from a software development lifecycle view. We classify the lifecycle of BTAI into four stages: Planning, data collection, model development, and system deployment/use. Particularly, we investigate and summarize the trustworthy issues that blockchain can achieve in the latter three stages, including (1) data transparency, privacy, and accountability; (2) model transparency, privacy, robustness, and fairness; and (3) robustness, privacy, transparency, and fairness of system deployment/use. Finally, we present essential open research issues and future work on developing BTAI systems.