[apendleton]

A lot of the scariest work in fake video lately has involved generative adversarial networks (GANs) whose whole optimization strategy as I understand it is to try to produce videos that can fool classifier/discriminator NNs, which are trained in parallel.

[yonilevy]

Right, and great point, but aren't the adversaries targeting a specific model? Are they agnostic to setups differences?

[webmaven]

Some approaches target multiple models to come up with more general attacks. It's also worth noting that manipulations that will fool humans are starting to pop up as well.