The Heat is On: Understanding and Mitigating Vulnerabilities of Thermal Image Perception in Autonomous Systems
Sri Hrushikesh Varma Bhupathiraju
Network and Distributed System Security (NDSS) Symposium 2026 · Day 3 · Network Security
**Thermal cameras** are increasingly integrated into autonomous systems -- robot taxis (**Waymo**, **Nuro**), robotic platforms (**RAS**), and drones (**DJI**, **Skydio**) -- to enhance perception in low-light conditions and adverse weather. This talk presents the **first security analysis of thermal camera signal processing**, uncovering three novel vulnerabilities in the **image acquisition**, **calibration**, and **equalization** pipelines that can be exploited using nothing more than a **$20 reptile heating lamp** and aluminum foil. The attacks achieve **100% missed detection** of genuine obstacles and **91% fake obstacle detection** in real-world driving scenarios at up to **40 km/h**, tested on three commercial thermal cameras: **FLIR Boson** (40% market share), **InfiRay T2S**, and **FPV XKC130**. Critically, the calibration attack produces **delayed artifacts** -- fake obstacles that appear at a controlled time **after the attack has terminated**, making it particularly stealthy. The researchers also design signal processing mitigations that address all three vulnerabilities simultaneously, accounting for their interdependence.
AI review
First security analysis of thermal camera signal processing, uncovering three exploitable vulnerabilities using a $20 heat lamp. The calibration attack -- which creates delayed phantom obstacles appearing after the attack source is removed -- is genuinely novel and operationally clever. Real-world validation at 40 km/h on commercial cameras used in autonomous vehicles.