Papers by Author: Jian Wang

Abstract: Neural network learning algorithms are widely used in medical diagnosis, bioinformatics, intrusion detection, homeland security and other fields. The common of these applications is that all of them need to extract patterns and predict trends from a large number of complex data. In these applications, how to protect the privacy of sensitive data and personal information from disclosure is an important issue. At present, the vast majority of existing neural network learning algorithms did not consider how to protect the data privacy in the process of learning. So this paper proposes two privacy-preserving back-propagation neural network protocols applied to horizontally partitioned data and vertically partitioned data separately. The two protocols are suitable for multiple participants in a distributed environment. The results of experiments show the difference of the test error rate between the proposed two protocols and the respective non-privacy preserving versions.

Abstract: Cloud computing seems to offer some incredible benefits for communicators: the availability of an incredible array of software applications, access to lightning-quick processing power, unlimited storage, and the ability to easily share and process information. All of this is available through your browser any time you can access the Internet. While this might all appear enticing, there remain issues of reliability, portability, privacy, and security. When our private data are out-sourced in cloud computing, we should guarantee the confidentiality and searchability of the private data. Our paper provides a new approach to avoid the disclosure of the sensitive attributes of users when user ask for service from the Service Provider (SP) in cloud computing.

Abstract: Some medical records are often added and deleted in the practical applications. The leakage of privacy information caused by re-publishing datasets with multiple sensitive attributes becomes more likely than any other publication styles. In this paper, we first systematically characterize the inference attacks and set the hierarchy sensitive attribute rules. Then we propose a novel privacy preserving model based on k-anonymity for re-publication of multiple sensitive datasets and verify the novel approach that can eliminate inference channel and effectively protect privacy information in re-publication of datasets with multiple sensitive attributes by specific example. Finally, we present the anonymization algorithm to achieve privacy against inference attack.