Related Experiment Video
Updated: Jan 13, 2026
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
LIMA: Towards building a non-invasive and stealthy real-world adversarial attack model for traffic sign recognition
Junbin Fang1, Yixuan Shen1, Yujing Sun2
1Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Jinan University, Guangzhou, 510632, China; Guangdong Provincial Engineering Technology Research Center on Visible Light Communication, and Guangzhou Municipal Key Laboratory of Engineering Technology on Visible Light Communication, Jinan University, Guangzhou, 510632, China; Department of Optoelectronic Engineering, Jinan University, Guangzhou, 510632, China.
Abstract:
Traffic sign recognition systems are crucial for autonomous driving safety. However, their susceptibility to adversarial attacks poses severe risks, potentially leading to catastrophic accidents. The purpose of adversarial attack research is to identify vulnerabilities in the systems, thereby improving understanding and response to these security threats. Unlike prior adversarial attacks, which are typically invasive, conspicuous, and impractical, our proposed attack operates non-invasively while remaining stealthy to human observers. Specifically, we exploit high-speed modulation of LED illumination and the rolling shutter mechanism of CMOS sensors to create imperceptible perturbations. By adjusting the LED flicker frequency, we effectively conduct denial-of-service attack and evasion attack. Extensive evaluations in both simulations and real-world scenarios confirm LIMA's effectiveness, with a 100% success rate across most distance-angle combinations and 69.67% success even against defense models.