06/12/2021

Unadversarial Examples: Designing Objects for Robust Vision

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

Keywords: robustness, adversarial robustness and security, vision

Abstract Paper Similar Papers

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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at NeurIPS 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 17:51 
 0
 0
 0
 0
 12:21 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 8:03 
 0
 0
 0
 0
 9:02 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 12:32 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 11:54 
 0
 0
 0
 0
 8:16 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 4:37 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 8:44 
 0
 0
 0
 0
 18:49 
 0
 0
 0
 0
 10:05 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 20:15 
 0
 0
 0
 0
 9:00 
 0
 0
 0
 0
 10:37 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 2:40 
 0
 0
 0
 0
 14:06 
 0
 1
 0
 0
 5:10 
 0
 0
 0
 0
 9:51