Reviews: Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples

This paper presents a way to create adversarial examples based on a task loss (e.g. The approach is tested on a few different domains (pose estimation, semantic segmentation, speech recognition). Overall the approach is nice and the results are impressive. My main issues with the paper (prompting my "marginal accept" decision) are: - The math and notation is confusing and contradictory in places, e.g. It needs to be cleaned up.