• We introduce AuRA, a ROS~2-based platform for security exploration of light-based attacks across interchangeable camera configurations and real-time perception tasks.

• We develop an independent, temporal-illumination attack module with runtime control over waveform, frequency, modulation depth, duty cycle, and phase shift.

• We conduct a cross-camera evaluation of rolling-shutter, global-shutter, and auto-controlled cameras under controlled and real-time conditions, demonstrating attack effects on traffic-sign classification, prediction confidence, and lane-following performance.

Publications:

• M. T. Islam, B. B. Yedla Ravi and M. R. Kabir, “AuRA: A ROS 2-based Platform for Camera Attack Exploration in Autonomous Vehicles,” 6th IEEE Cyber Awareness and Research Symposium (CARS), 2026

• M. T. Islam and M. R. Kabir, “Vision-Based Lane Following and Traffic Sign Recognition for Resource-Constrained Autonomous Vehicles,” 3rd International Conference on Intelligent Systems, Blockchain, and Communication Technologies (ISBCom), 2026