Srinivas Devadas News Today

It is time for computer designers to work smart instead of strong, which is just what Devadas is doing.

MIT researchers created a new data privacy metric, Probably Approximately Correct (PAC) Privacy, and built an algorithm based on this metric that can automatically determine the minimal amount of randomness that needs to be added to a machine-learning model to protect sensitive data from an adversary.

MIT researchers have developed a novel privacy-preserving protocol that could enable an algorithm that provides recommendations to guarantee a user’s personal information remains secure while ensuring recommendation results are accurate. Their technique is so efficient it can run on a smartphone over a very slow network.