Narrow Results

Although deep learning models have shown promising results in solving problems related to image recognition or natural language processing, they do not match how the biological brain works. Some of the differences include the amount of energy consumed, the way neurons communicate, or the way they learn. To close the gap between artificial neural networks and biological ones, researchers proposed the spiking neural network. Layered Spiking Neural P systems (LSN P systems) are networks of spiking neurons used to solve various classification problems. In this paper, we study the LSN P systems in the context of a federated learning client–server architecture over horizontally partitioned data. We analyze the privacy implications of pre-trained LSN P systems through membership inference attacks. We also perform experiments to assess the performance of an LSN P system trained in the federated learning setup. Our findings suggest that LSN P systems demonstrate higher accuracy and faster convergence compared to federated algorithms based on either perceptron or spiking neural networks.

Recently, growing privacy concerns have received more and more attention and it becomes a significant topic on how to preserve private-sensitive information from being violated in distributed cooperative computation. In this paper, we first propose a novel-general privacy-preserving online analytical processing model based on secure multiparty computation. Then, based on the new model, two schemes to privacy-preserving count aggregate query over both horizontally partitioned data and vertically partitioned data are proposed. Additionally, we also propose several efficient subprotocols that serve as the basic secure buildings. Furthermore, we analyze correctness, security, communication cost, and computation complexity of our proposed protocols, and show that the new schemes are secure, having good linear complexity and that the query results are exactly accurate.

Statistics such as $k$th minimum value play a crucial role in our data-driven society, for example by informing decision-making. In this paper, we propose an efficient privacy-preserving protocol that allows a group of users who do not trust each other, for example in a peer-to-peer (P2P) network, to jointly calculate the $k$th minimum value. Specifically, in our proposed protocol each user’s data is converted to a binary bit string following a certain rule. Then, the bits at the same position are aggregated from the leftmost to the rightmost. As far as we know, this is the first published scheme to obtain $k$th minimum value in a P2P network without affecting users’ privacy. We also remark that the proposed protocol can be easily generalized to compute other statistics, such as maximum value, minimum value, and median value, while achieving high efficiency in a privacy-preserving P2P network. We then demonstrate that the proposed protocol achieves forward security and is resilient to a range of external and internal attacks.

Driven by mutual benefits, there is a demand for transactional data sharing among organizations or parties for research or business analysis purpose. It becomes an essential concern to provide privacy-preserving data sharing and meanwhile maintain data utility, due to the fact that transactional data may contain sensitive personal information. Existing privacy-preserving methods, such as k-anonymity and l-diversity, cannot handle high-dimensional sparse data well, since they would bring about much data distortion in the anonymization process. In this paper, we use bipartite graphs with node attributes to model high-dimensional sparse data, and then propose a privacy-preserving approach for sharing transactional data in a new vision, in which the bipartite graph is anonymized into a weighted bipartite graph by clustering node attributes. Our approach can maintain privacy of the associations between entities and resist certain attackers with knowledge of partial items. Experiments have been performed on real-life data sets to measure the information loss and the accuracy of answering aggregate queries. Experimental results show that the approach improves the balance of performance between privacy protection and data utility.

This paper introduces a novel hybrid filter-based ensemble multi-class classification model for distributed privacy-preserving applications. The conventional privacy-preserving multi-class learning models have limited capacity to enhance the true positive rate, mainly due to computational time and memory constraints, as well as the static nature of metrics for parameter optimization and multi-class perturbation processes. In this research, we develop the proposed model on large medical and market databases with the aim of enhancing multi-party data confidentiality through a security framework during the privacy-preserving process. Moreover, we also introduce a secure multi-party data perturbation process to improve computational efficiency and privacy-preserving performance. Experimental results were evaluated on different real-time privacy-preserving datasets, such as medical and market datasets, using different statistical metrics. The evaluation results demonstrate that the proposed multi-party-based multi-class privacy-preserving model performs statistically better than conventional approaches.

With the rapid development of the e-business, social networking and enterprise information system, the volume of data produced by individuals and enterprises is increasing rapidly, resulting in a rise of cloud storage as an increasing number of enterprises and individuals store their data in the cloud for greater flexibility and economic savings. However the risk of leakage of sensitive user data is still prevalent. Although several keyword search schemes over encrypted data with privacy preserving has been previously proposed, we propose a novel scheme to support the multi-keywords fuzzy search while also supporting Chinese search. We utilize the locality-sensitive hashing technique to solve the fuzzy match and the experiments on real-world data demonstrate that our proposed scheme is accurate, efficient and secure.