Re:The US military is funding an effort to catch deepfakes a...
by supermdguy on Wednesday May 23, 2018 @09:36PM
(#17140256)
It's feasible to design a reinforcement learning based network that uses output from a non-differentiable deepfake detector as a component of the loss function.
Pretty much nothing except other neural networks are differentiable, unless you put effort into designing them to be.