Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
Jiahuan Long, Tingsong Jiang, Hanqing Liu, Chao Ma, Weien Zhou, Yang Yang, Wen Yao
Abstract
Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous appearance makes them difficult to deploy in real-world scenarios. In this paper, we propose a thermally activated adversarial wearable designed to ensure adaptability and effectiveness in complex real-world environments. The system integrates thermochromic dyes with flexible heating units to induce visually dynamic adversarial patterns on clothing surfaces. In its default state, the clothing appears as an ordinary black T-shirt. Upon heating via an embedded thermal unit, hidden adversarial patterns on the fabric are activated, allowing the wearer to effectively evade detection across both visible and infrared modalities. Physical experiments demonstrate that the adversarial wearable achieves rapid texture activation within 50 seconds and maintains an adversarial success rate above 80% across diverse real-world surveillance environments. This work demonstrates a new pathway toward physically grounded, user-controllable anti-AI systems, highlighting the growing importance of proactive adversarial techniques for privacy protection in the age of ubiquitous AI surveillance.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 59cb8f9b-2d68-43b5-a759-44cd94e36b31Builds on19
- Adversarial Texture for Fooling Person Detectors in the Physical WorldZhanhao Hu, Siyuan Huang, Xiaopei Zhu, Fuchun Sun et al.CVPR 2022 · 125 citations
- Exploring Frequency Adversarial Attacks for Face Forgery DetectionShuai Jia, Chao Ma, Taiping Yao, Bangjie Yin et al.CVPR 2022 · 78 citations
- Unified Adversarial Patch for Cross-modal Attacks in the Physical WorldXingxing Wei, Yao Huang, Yitong Sun, Jie YuICCV 2023 · 44 citations
- Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous DrivingJunhao Zheng, Chenhao Lin, Jiahao Sun, Zhengyu Zhao et al.CVPR 2024 · 36 citations
- REAP: A Large-Scale Realistic Adversarial Patch BenchmarkNabeel Hingun, Chawin Sitawarin, Jerry Li, David A. WagnerICCV 2023 · 30 citations
Related papers
- Infrared Invisible Clothing: Hiding from Infrared Detectors at Multiple Angles in Real WorldXiaopei Zhu, Zhanhao Hu, Siyuan Huang, Jianmin Li et al.CVPR 2022 · 67 citations
- AdvDisplay: Adversarial Display Assembled by Thermoelectric Cooler for Fooling Thermal Infrared DetectorsHao Li, Fanggao Wan, Yue Su, Yue Wu et al.AAAI 2025
- Physically Adversarial Infrared Patches with Learnable Shapes and LocationsXingxing Wei, Jie Yu, Yao HuangCVPR 2023
- Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D ModelingZhanhao Hu, Wenda Chu, Xiaopei Zhu, Hui Zhang et al.CVPR 2023
- Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object DetectionYixing Yong, Jian Wang, Ming Lei, Lijun He et al.ICML 2026
