pith. sign in

arxiv: 1904.05712 · v1 · pith:YUXHZKEEnew · submitted 2019-04-11 · 💻 cs.CV · cs.CR

Reconstructing Network Inputs with Additive Perturbation Signatures

classification 💻 cs.CV cs.CR
keywords modelabilityadditiveinputsaccessamountdemonstratingevaluate
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.