pith. sign in

arxiv: 2208.06962 · v1 · pith:QDR6M4THnew · submitted 2022-08-15 · 💻 cs.CV · cs.LG

InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee

classification 💻 cs.CV cs.LG
keywords person-trackingadversarialinvisibiliteesystemsangle-agnosticblack-boxdetectionmethod
0
0 comments X
read the original abstract

After a survey for person-tracking system-induced privacy concerns, we propose a black-box adversarial attack method on state-of-the-art human detection models called InvisibiliTee. The method learns printable adversarial patterns for T-shirts that cloak wearers in the physical world in front of person-tracking systems. We design an angle-agnostic learning scheme which utilizes segmentation of the fashion dataset and a geometric warping process so the adversarial patterns generated are effective in fooling person detectors from all camera angles and for unseen black-box detection models. Empirical results in both digital and physical environments show that with the InvisibiliTee on, person-tracking systems' ability to detect the wearer drops significantly.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.