3D Invisible Cloak
Mingfu Xue, Can He, Zhiyu Wu, Jian Wang, Zhe Liu, Weiqiang Liu

TL;DR
This paper introduces a 3D physical stealth attack using adversarial patches to create an invisible cloak, enabling individuals to evade person detectors in complex real-world scenarios with high success rates.
Contribution
It proposes a novel 3D transformation-based method for generating physical adversarial patches that function as invisible cloaks in real-world conditions.
Findings
Attack success rate in digital domain is 86.56%.
Physical world stealth attack success rates are 100% static, 77% dynamic.
Method outperforms existing approaches in robustness and effectiveness.
Abstract
In this paper, we propose a novel physical stealth attack against the person detectors in real world. The proposed method generates an adversarial patch, and prints it on real clothes to make a three dimensional (3D) invisible cloak. Anyone wearing the cloak can evade the detection of person detectors and achieve stealth. We consider the impacts of those 3D physical constraints (i.e., radian, wrinkle, occlusion, angle, etc.) on person stealth attacks, and propose 3D transformations to generate 3D invisible cloak. We launch the person stealth attacks in 3D physical space instead of 2D plane by printing the adversarial patches on real clothes under challenging and complex 3D physical scenarios. The conventional and 3D transformations are performed on the patch during its optimization process. Further, we study how to generate the optimal 3D invisible cloak. Specifically, we explore how to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · Video Surveillance and Tracking Methods · Advanced Neural Network Applications
