Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer

Hsueh-Ti Derek Liu, Michael Tao, Chun-Liang Li, Derek Nowrouzezahrai, Alec Jacobson

Abstract: Enabled by a novel differentiable renderer, we propose a new metric that has real-world implications for evaluating adversarial machine learning algorithms, resolving the lack of realism of the existing metric based on pixel norms.