Infrared Adversarial Car Stickers
Xiaopei Zhu, Yuqiu Liu, Zhanhao Hu, Jianmin Li, Xiaolin Hu

TL;DR
This paper introduces a novel 3D infrared adversarial sticker method for cars, effectively making them invisible to infrared detectors across various conditions, with high success and transferability.
Contribution
It presents a new 3D modeling approach for infrared adversarial stickers on cars, improving attack success rates and transferability across multiple detectors.
Findings
Achieved 91.49% attack success rate on real cars.
Stickers successfully hid cars from multiple detectors at various angles and distances.
High transferability of attack across different infrared detectors.
Abstract
Infrared physical adversarial examples are of great significance for studying the security of infrared AI systems that are widely used in our lives such as autonomous driving. Previous infrared physical attacks mainly focused on 2D infrared pedestrian detection which may not fully manifest its destructiveness to AI systems. In this work, we propose a physical attack method against infrared detectors based on 3D modeling, which is applied to a real car. The goal is to design a set of infrared adversarial stickers to make cars invisible to infrared detectors at various viewing angles, distances, and scenes. We build a 3D infrared car model with real infrared characteristics and propose an infrared adversarial pattern generation method based on 3D mesh shadow. We propose a 3D control points-based mesh smoothing algorithm and use a set of smoothness loss functions to enhance the smoothness…
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
TopicsFire Detection and Safety Systems · Advanced Measurement and Detection Methods
MethodsBNB Customer Service Number +1-833-534-1729 · Attention Is All You Need · Sparse Evolutionary Training · Average Pooling · Global Average Pooling · Linear Layer · Position-Wise Feed-Forward Layer · Batch Normalization · 1x1 Convolution · Label Smoothing
