Party Data Research Articles

B-LNN: Inference-time linear model for secure neural network inference

Machine Learning as a Service (MLaaS) provides clients with well-trained neural networks for predicting private data. Conventional prediction processes of MLaaS require clients to send sensitive inputs to the server, or proprietary models must be stored on the client-side device. The former reveals client privacy, while the latter harms the interests of model providers. Existing works on privacy-preserving MLaaS introduce cryptographic primitives to allow two parties to perform neural network inference without revealing either party's data. However, nonlinear activation functions bring high computational overhead and response delays to the inference process of these schemes.In this paper, we analyze the mechanism by which activation functions enhance model expressivity, and design an activation function S-cos that is friendly to secure neural network inference. Our proposed S-cos can be re-parameterized into a linear layer during the inference phase. Further, we propose an inference-time linear model called Beyond Linear Neural Network (B-LNN) equipped with S-cos, which exhibits promising performance on several benchmark datasets.

Privacy-Preserving Gaussian Process Regression – A Modular Approach to the Application of Homomorphic Encryption

Much of machine learning relies on the use of large amounts of data to train models to make predictions. When this data comes from multiple sources, for example when evaluation of data against a machine learning model is offered as a service, there can be privacy issues and legal concerns over the sharing of data. Fully homomorphic encryption (FHE) allows data to be computed on whilst encrypted, which can provide a solution to the problem of data privacy. However, FHE is both slow and restrictive, so existing algorithms must be manipulated to make them work efficiently under the FHE paradigm. Some commonly used machine learning algorithms, such as Gaussian process regression, are poorly suited to FHE and cannot be manipulated to work both efficiently and accurately. In this paper, we show that a modular approach, which applies FHE to only the sensitive steps of a workflow that need protection, allows one party to make predictions on their data using a Gaussian process regression model built from another party's data, without either party gaining access to the other's data, in a way which is both accurate and efficient. This construction is, to our knowledge, the first example of an effectively encrypted Gaussian process.

Outsourcing privacy-preserving ID3 decision tree over horizontally partitioned data for multiple parties

Today, many small and medium-sized companies want to share data for data mining; however, privacy and security concerns restrict such data sharing. Privacy-preserving data mining has emerged as a solution to this problem. Nevertheless, the traditional cryptographic solutions are too inefficient and infeasible to allow the large-scale analytics needed for big data. In this paper, we focus on the outsourcing of privacy-preserving ID3 decision trees over horizontally partitioned data for multiple parties. We outsource most of the protocol computation to the cloud and propose the OPPWAP to protect users' data privacy. By this method, each party can have the correct results calculated with data from other parties and the cloud, and each party's data are kept private from other parties and the cloud. Our findings indicate that an increase in the number of participating parties results in a slight computing cost increase on the user's side.

Outsourcing privacy-preserving ID3 decision tree over horizontal partitioned data for multiple parties

Today, many small and medium-sized companies want to share data for data mining; however, privacy and security concerns restrict such data sharing. Privacy-preserving data mining has emerged as a solution to this problem. Nevertheless, the traditional cryptographic solutions are too inefficient and infeasible to allow the large-scale analytics needed for big data. In this paper, we focus on the outsourcing of privacy-preserving ID3 decision trees over horizontally partitioned data for multiple parties. We outsource most of the protocol computation to the cloud and propose the OPPWAP to protect users' data privacy. By this method, each party can have the correct results calculated with data from other parties and the cloud, and each party's data are kept private from other parties and the cloud. Our findings indicate that an increase in the number of participating parties results in a slight computing cost increase on the user's side.