Decision tree and its generalization of random forests are a simple yet powerful machine learning model for many classification and regression problems. Recent works propose how to privately evaluate a decision tree in a two-party setting where the feature vector of the client or the decision tree model (such as the threshold values of its nodes) is kept secret from another party. However, these works cannot be extended trivially to support the outsourcing setting where a third-party who should not have access to the model or the query. Furthermore, their use of aninteractivecomparison protocol does not support branching program, hence requires interactions with the client to determine the comparison result before resuming the evaluation task. In this paper, we propose the first secure protocol for collaborative evaluation of random forests contributed by multiple owners. They outsource evaluation tasks to a third-party evaluator. Upon receiving the client's encrypted inputs, the cloud evaluates obliviously on individually encrypted random forest models and calculates the aggregated result. The system is based on our new secure comparison protocol, secure counting protocol, and a multi-key somewhat homomorphic encryption on top of symmetric-key encryption. This allows us to reduce communication overheads while achieving round complexity lower than existing work.

Geosocial applications collect (and record) users' precise location data to perform proximity computations, such as notifying a user or triggering a service when a friend is within geographic proximity. With the growing popularity of mobile devices that have sophisticated localization capability it becomes more convenient and tempting to share location data. But the precise location data in plaintext not only exposes user's whereabouts but also mobility patterns that are sensitive and cannot be changed easily. This paper proposes cryptographic protocols on top of spatial cloaking to reduce the resolution of location and balance between data utility and privacy. Specifically we interest in the setting that allows users to send periodic updates of precise coordinates and define privacy preferences to control the granularity of the location, both in an encrypted format. Our system supports three kinds of user queries --- "Where is this user?", "Who is nearby?", and "How close is this user from another user?". Also, we develop a new algorithm to improve the multidimensional data access by reducing significant masking error. Our prototype and various performance evaluations on different platforms demonstrated that our system is practical.