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.
@article{arxiv.2208.06962,
title = {InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee},
author = {Yaxian Li and Bingqing Zhang and Guoping Zhao and Mingyu Zhang and Jiajun Liu and Ziwei Wang and Jirong Wen},
journal= {arXiv preprint arXiv:2208.06962},
year = {2022}
}
Comments
12 pages, 10 figures and the ICANN 2022 accpeted paper