Blockchains for Artificial Intelligence of Things: A Comprehensive Survey

With the rapid advances in information and communication technologies, the Internet of Things (IoT) has become large and complex, bearing tremendous amounts of data and running devices in various scenarios. Leveraging artificial intelligence (AI) technologies, IoT can achieve superior information extraction, data analytics, and decision making, which has resulted in the revolutionized AI of Things (AIoT). AIoT can alleviate the pressure of storage, computation, and communication. Despite the promising features brought by combining AI technologies into IoT infrastructure, AIoT systems still face some serious challenges including inadequate efficiency, violation of security and privacy, lack of trust, and insufficient incentive. Blockchain featured by its distributed consensus and incentive mechanisms can be a promising technology for addressing the challenges in AIoT. AIoT employing blockchain is evolving with expectations of achieving efficient, secure, and trusted network activities. In this article, we first introduce the background of AIoT and blockchain. Then, we discuss the motivations for employing blockchain with its characteristics in AIoT. Furthermore, we comprehensively review existing solutions on blockchain for AIoT systems from the aspects of efficiency, security, privacy, trust, and incentive. Finally, we discuss the challenges and future research directions on blockchain for AIoT.

I. Introduction

With the continuous development of Internet of Things (IoT) applications, large-scale connected IoT devices are expected to bring huge storage, computation, and communication overhead for the network environment [1]. Due to the advances and breakthroughs in artificial intelligence (AI) technologies, IoT has introduced emerging AI strategies or machine learning (ML) algorithms to achieve intelligent networking operation and management. The integration of IoT and AI has formed an intelligent ecosystem called AI of Things (AIoT) to achieve the implementation of human intelligent behaviors [2], [3]. AIoT systems can collect, analyze and process the data that they acquire from the surrounding environment. AIoT systems can also communicate with other networking agents, such as users or other networking systems. They can also learn from experience and respond to the external environment accordingly. Compared with traditional IoT systems, AIoT has the ability to perform big data analysis and mining, which relies on basic AI infrastructures of data representation, data storage, and data management. The solving problems AIoT deals with are often of high computational complexity. Different from traditional IoT systems, AIoT systems often adopt heuristic-solving algorithms which are data-dependent to a large extent. In addition, by perceiving, learning, and interacting with the external environment, AIoT outperforms IoT without AI in adaptability.