InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
This addresses privacy concerns for individuals in public spaces, though it is an incremental improvement on existing adversarial attack methods.
The paper tackles the problem of privacy invasion by person-tracking systems by proposing InvisibiliTee, a method that creates printable adversarial patterns on T-shirts to cloak wearers, resulting in a significant drop in detection ability in both digital and physical environments.
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.