Reconstructing Network Inputs with Additive Perturbation Signatures

04/11/2019
by   Nick Moran, et al.
0

In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to model outputs and the ability evaluate the model on additive perturbations to the input.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset