There is growing concern about image privacy due to the popularity of social
media and photo devices, along with increasing use of face recognition systems.
However, established image de-identification techniques are either too subject
to re-identification, produce photos that are insufficiently realistic, or
both. To tackle this, we present a novel approach for image obfuscation by
manipulating latent spaces of an unconditionally trained generative model that
is able to synthesize photo-realistic facial images of high resolution. This
manipulation is done in a way that satisfies the formal privacy standard of
local differential privacy. To our knowledge, this is the first approach to
image privacy that satisfies $varepsilon$-differential privacy emph{for the
person.}

Go to Source of this post
Author Of this post: <a href="http://arxiv.org/find/cs/1/au:+Li_T/0/1/0/all/0/1">Tao Li</a>, <a href="http://arxiv.org/find/cs/1/au:+Clifton_C/0/1/0/all/0/1">Chris Clifton</a>

By admin