Real-time Spread Burst Detection in Data Streaming.

Data streaming has many applications in network monitoring, web services, e-commerce, stock trading, social networks, and distributed sensing. This paper introduces a new problem of real-time burst detection in flow spread, which differs from the traditional problem of burst detection in flow size. It is practically significant with potential applications in cybersecurity, network engineering, and trend identification on the Internet. It is a challenging problem because estimating flow spread requires us to remember all past data items and detecting bursts in real time requires us to minimize spread estimation overhead, which was not the priority in most prior work. This paper provides the first efficient, real-time solution for spread burst detection. It is designed based on a new real-time super spreader identifier, which outperforms the state of the art in terms of both accuracy and processing overhead. The super spreader identifier is in turn based on a new sketch design for real-time spread estimation, which outperforms the best existing sketches.

Training Medical-Diagnosis Neural Networks on the Cloud with Privacy-Sensitive Patient Data from Multiple Clients.

Artificial neural networks (ANNs) are changing the paradigm in medical diagnosis. However, it remains an open problem how to outsource the model training operations to the cloud while protecting the privacy of distributed patient data. Homomorphic encryption suffers from high overhead over data independently encrypted from numerous sources, differential privacy introduces a high level of noise which drastically increases the number of patient records needed to train a model, while federated learning requires all participants to perform synchronized local training that counters our goal of outsourcing all training operations to the cloud. This paper proposes to use matrix masking for outsourcing all model training operations to the cloud with privacy protection. After outsourcing their masked data to the cloud, the clients do not need to coordinate and perform any local training operations. The accuracy of the models trained by the cloud from the masked data is comparable to the accuracy of the optimal benchmark models that are trained directly from the original raw data. Our results are confirmed by experimental studies on privacy-preserving cloud training of medical-diagnosis neural network models based on real-world Alzheimer's disease data and Parkinson's disease data.

On Outsourcing Artificial Neural Network Learning of Privacy-Sensitive Medical Data to the Cloud.

Machine learning and artificial neural networks (ANNs) have been at the forefront of medical research in the last few years. It is well known that ANNs benefit from big data and the collection of the data is often decentralized, meaning that it is stored in different computer systems. There is a practical need to bring the distributed data together with the purpose of training a more accurate ANN. However, the privacy concern prevents medical institutes from sharing patient data freely. Federated learning and multi-party computation have been proposed to address this concern. However, they require the medical data collectors to participate in the deep-learning computations of the data users, which is inconvenient or even infeasible in practice. In this paper, we propose to use matrix masking for privacy protection of patient data. It allows the data collectors to outsource privacy-sensitive medical data to the cloud in a masked form, and allows the data users to outsource deep learning to the cloud as well, where the ANN models can be trained directly from the masked data. Our experimental results on deep-learning models for diagnosis of Alzheimer's disease and Parkinson's disease show that the diagnosis accuracy of the models trained from the masked data is similar to that of the models from the original patient data.