An increasing number of organizations are moving their analytics workloads into the cloud to take advantage of the elasticity and cost savings. However, the risk of data breaches is hampering this trend. While hardware enclaves promise a much needed solution to data confidentiality and secure execution of arbitrary computation, they still suffer from a significant leakage vector: access pattern leakage. We propose Opaque, a distributed data analytics platform supporting a wide range of queries while providing strong security guarantees for both access patterns and integrity protection.
Wenting Zheng
Raluca Popa