Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
This work addresses privacy protection against AI surveillance for individuals by enabling user-controllable, inconspicuous adversarial clothing, representing an incremental advancement in physically grounded anti-AI systems.
The paper tackles the problem of conspicuous adversarial patches in AI surveillance by proposing a thermally activated adversarial wearable that integrates thermochromic dyes and heating units to create dynamic patterns on clothing, achieving over 80% adversarial success rate in real-world environments.
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.