We are happy to share that the paper “S2Dedup: SGX-enabled Secure Deduplication” was accepted at SYSTOR21!
Briefly, this work leverages intel SGX to enable privacy-preserving deduplication at untrusted servers. Also we provide an open-source data plane prototype, built with SPDK, that supports multiple secure schemes!
Deduplication is more and more used to optimize the performance and reduce the storage costs of Big Data applications (e.g., Deep Learning frameworks) that deal with large quantities of information.
Our solution enables this technique at third-party infrastructures, such as HPC centers, without compromising the privacy of users’ sensitive data.