EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving

Ce Zhou, Qiben Yan, Daniel Kent, Guangjing Wang, Weikang Ding, Ziqi Zhang, Hayder Radha

ACM Transactions on Cyber-Physical Systems · 31.10.2026 · 10 (4) · 1-31

DOI: 10.1145/3812541 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Cyber-Physical Systems, online erschienen am 13.07.2026. Verfasst von Ce Zhou und 6 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this article, we explore the vulnerabilities of MDE algorithms in AD systems, presenting \(LensAttack\) , a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. \(LensAttack\) encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of \(LensAttack\) on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that \(LensAttack\) can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.

Förderung

  • U.S. National Science Foundation

Zitieren

APA

Zhou, C., Yan, Q., Kent, D., Wang, G., Ding, W., Zhang, Z., & Radha, H. (2026). Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving. ACM Transactions on Cyber-Physical Systems, 10(4), 1-31. https://doi.org/10.1145/3812541

Vancouver

Zhou C, Yan Q, Kent D, Wang G, Ding W, Zhang Z, et al. Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving. ACM Transactions on Cyber-Physical Systems. 2026;10(4):1-31. doi:10.1145/3812541

BibTeX
@article{Zhou2026,
  author = {Zhou, Ce and Yan, Qiben and Kent, Daniel and Wang, Guangjing and Ding, Weikang and Zhang, Ziqi and Radha, Hayder},
  title = {Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving},
  journal = {ACM Transactions on Cyber-Physical Systems},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {1--31},
  doi = {10.1145/3812541}
}
Kostenlos starten →