With the rapid development and application of artificial intelligence technology, medical data play an increasingly important role in the medical field. However, there are privacy protection and data ownership issues in the process of data sharing, which brings difficulties to machine learning and data mining. On the one hand, for fear that they may risk being held accountable by users or even breaking the law due to these issues, healthcare providers are reluctant to share medical data. On the other hand, users are also reluctant to share medical data due to the possibility of privacy disclosure in the data sharing process. To improve the security and privacy of shared medical data, we propose a user-centered medical data sharing scheme for privacy-preserving machine learning. Our solution combines blockchain and a trusted execution environment to ensure that adversaries cannot steal the ownership and control of user data during sharing. A blockchain-based noninteractive key sharing scheme is proposed that allows only the users and the TEE to decrypt the shared data. At the same time, we design an auditing mechanism to facilitate users to audit the sharing process. The security analysis shows that the scheme ensures the privacy and security of user data during storage and sharing. We have completed simulation experiments to demonstrate the effectiveness and efficiency of our scheme.

To ensure the security of data, more and more users encrypt data for storage, which makes the high-efficiency ciphertext search problem in the context of cloud storage a research hotspot. Existing solutions still suffer from many vexatious problems, such as the need to maintain complex index structures and the unsatisfactory application of homomorphic schemes. To solve the above problems, this paper proposes a multiuser ciphertext search scheme based on blockchain and SGX. Our scheme uses blockchain and SGX to protect keywords and data privacy and complete decryption and keywords search of ciphertext data which does not need pregenerated indexes or preselected keywords. Second, for a multiuser scenario, a smart contract is designed to verify authorization requests and manage multiple authorized users. Finally, we give security analysis, function comparison, and performance analysis to prove the security and feasibility of our scheme. Experiments show that our scheme has effectively met practical requirements.

No abstract