Mar 1, 2017 · Abstract:Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate ...

May 7, 2017 · Abstract—Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict.

It is shown that requiring perfect distortion-based security is more frugal than requiring perfect information-theoretic secrecy even for block length one ...

The study claims that data after random projection satisfies the entropy-maximizing criterion which is needed by the semantic hashing. The binary codes after ...

The idea of using finite block length (and even single-shot) distortion as a performance measure was initiated in [16] , where schemes for single shot ...

Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate system actions.

A distortion based approach for protecting inferences. Tsai, C., Agarwal, G. K., Fragouli, C., & Diggavi, S. In 2017 IEEE international symposium on ...

Bibliographic details on A Distortion Based Approach for Protecting Inferences.

A distortion based approach for protecting inferences. CY Tsai, GK Agarwal, C Fragouli, S Diggavi. 2017 IEEE international symposium on information theory (ISIT) ...