Adversarial Clothing

DSP postdoc alum Thomas Goldstein has launched a new clothing line that evades detection by machine learning vision algorithms.

This stylish pullover is a great way to stay warm this winter, whether in the office or on-the-go. It features a stay-dry microfleece lining, a modern fit, and adversarial patterns the evade most common object detectors. In this demonstration, the YOLOv2 detector is evaded using a pattern trained on the COCO dataset with a carefully constructed objective.

Paper:  Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors by Z. Wu, S-N. Lim, L. Davis, Tom Goldstein, October 2019

Buy online

New Yorker article:  Dressing for the Surveillance Age

Leave a Reply

Your email address will not be published. Required fields are marked *