Unadversarial Examples: Designing Objects for Robust VisionDownload PDF

21 May 2021, 20:47 (edited 21 Jan 2022)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: adversarial robustness, adversarial examples, computer vision
  • TL;DR: We introduce unadversarial examples; objects explicitly designed to be robustly classified.
  • Abstract: 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.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/microsoft/unadversarial
14 Replies