Unadversarial Examples: Designing Objects for Robust Vision

Hadi Salman · Andrew Ilyas · Logan Engstrom · Sai Vemprala · Aleksander Madry · Ashish Kapoor

Keywords: [ Adversarial Robustness and Security ] [ Robustness ] [ Vision ]


We study a class of computer vision settings wherein one can modify the design of the objects being recognized. We develop a framework that leverages this capability---and deep networks' unusual sensitivity to input perturbations---to design ``robust objects,'' i.e., objects that are explicitly optimized to be confidently classified. Our framework yields improved performance on standard benchmarks, a simulated robotics environment, and physical-world experiments.

Chat is not available.