COVID-19 is a serious epidemic that not only endangers human health, but also wreaks havoc on the development of society. Recently, there has been research on using artificial intelligence (AI) techniques for COVID-19 detection. As AI has entered the era of big models, deep learning methods based on pre-trained models (PTMs) have become a focus of industrial applications. Federated learning (FL) enables the union of geographically isolated data, which can address the demands of big data for PTMs. However, the incompleteness of the healthcare system and the untrusted distribution of medical data make FL participants unreliable, and medical data also has strong privacy protection requirements. Our research aims to improve training efficiency and global model accuracy using PTMs for training in FL, reducing computation and communication. Meanwhile, we provide a secure aggregation rule using differential privacy and fully homomorphic encryption to achieve a privacy-preserving Byzantine robust federal learning scheme. In addition, we use blockchain to record the training process and we integrate a Byzantine fault tolerance consensus to further improve robustness. Finally, we conduct experiments on a publicly available dataset, and the experimental results show that our scheme is effective with privacy-preserving and robustness. The final trained models achieve better performance on the positive prediction and severe prediction tasks, with an accuracy of 85.00% and 85.06%, respectively. Thus, this indicates that our study is able to provide reliable results for COVID-19 detection.

With the rapid development of science and technology, enterprises will provide their customers with cloud data storage services. These massive amounts of data bring huge management costs to enterprises. Therefore, enterprises choose to store their data in professional cloud service providers and have third-party auditors check the integrity of cloud data to ensure security. Although the appearance of auditors reduces the enormous calculation pressure on enterprises, if the number of auditors is not limited, it will also bring an expensive management burden to enterprises. At the same time, in the process of performing data integrity auditing on behalf of the enterprise, auditors may be interested in some sensitive information of the enterprise’s customers (such as customer’s identity and specific content of customer data). Therefore, this paper proposes a remote data integrity auditing scheme based on designated verifiers. An essential feature of the scheme is that the auditor cannot obtain any customer’s identity information and data in the process of auditing; data integrity, the anonymity of the user’s identity, and data privacy are maintained in the process of auditing. Both theoretical analysis and experimental results show that our scheme is efficient and feasible.