Timezone: »

 
Poster
Unadversarial Examples: Designing Objects for Robust Vision
Hadi Salman · Andrew Ilyas · Logan Engstrom · Sai Vemprala · Aleksander Madry · Ashish Kapoor

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @
in Poster Session 2 »

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.

Keywords: Robustness · Adversarial Robustness and Security · Vision

Author Information

Hadi Salman (MIT)
Andrew Ilyas (MIT)
Logan Engstrom (MIT)
Sai Vemprala (Microsoft)
Aleksander Madry (MIT)

Aleksander Madry is the NBX Associate Professor of Computer Science in the MIT EECS Department and a principal investigator in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). He received his PhD from MIT in 2011 and, prior to joining the MIT faculty, he spent some time at Microsoft Research New England and on the faculty of EPFL. Aleksander's research interests span algorithms, continuous optimization, science of deep learning and understanding machine learning from a robustness perspective. His work has been recognized with a number of awards, including an NSF CAREER Award, an Alfred P. Sloan Research Fellowship, an ACM Doctoral Dissertation Award Honorable Mention, and 2018 Presburger Award.

Ashish Kapoor (Microsoft)

More from the Same Authors