Abstract:In recent years, artificial intelligence has been rapidly advancing. Artificial intelligence system has penetrated our life and has become an indispensable part of our life. However, artificial intelligence systems require a large amount of data to train models, and data disturbances will affect their results. What's more, with the business form changing, the scale becoming more complex, the trustworthiness of the artificial intelligence systems has been getting more and more attention. Firstly, based on summarizing the trustworthiness attributes proposed by various organizations and scholars, we introduce the nine trustworthiness attributes of artificial intelligence. Next, we present the existing AI systems measurement method for the data, model, and result trustworthiness, and propose a artificial intelligence trustworthy evidence collection method. Then, we discuss the trustworthiness measurement model of AI systems. Combined with existing attributes-based software trustworthiness measurement methods and blockchain technology, we propose an artificial intelligence system trustworthiness measurement framework, including the decomposition of trustworthiness attributes and evidence acquisition method, the federation trustworthiness measurement model, and the blockchain-based artificial intelligence trustworthiness measurement structure. Finally, we analyzed the opportunities and challenges of trustworthiness measurement technology for artificial intelligence systems.