Timezone: »

 
Poster
Detection as Regression: Certified Object Detection with Median Smoothing
Ping-yeh Chiang · Michael Curry · Ahmed Abdelkader · Aounon Kumar · John Dickerson · Tom Goldstein

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1579
in Poster Session 6 »
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive. This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Then, to enable certified regression, where standard mean smoothing fails, we propose median smoothing, which is of independent interest. We obtain the first model-agnostic, training-free, and certified defense for object detection against $\ell_2$-bounded attacks.
Keywords: Unsupervised Learning · Perception · Algorithms · Applications -> Robotics; Neuroscience and Cognitive Science

Author Information

Ping-yeh Chiang (University of Maryland, College Park)
Michael Curry (University of Maryland)
Ahmed Abdelkader (University of Maryland, College Park)
Aounon Kumar (University of Maryland, College Park)
John Dickerson (University of Maryland)
Tom Goldstein (University of Maryland)

More from the Same Authors