Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Optical Lens Attack on Deep Learning Based Monocular Depth Estimation

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

TL;DR

This paper introduces LensAttack, a physical attack that involves strategically placing optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths, and simulates the attack and evaluates its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models.

Abstract

Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a detected obstacle or changing lanes to avoid collision. In this paper, we investigate the security risks associated with monocular vision-based depth estimation algorithms utilized by AD systems. By exploiting the vulnerabilities of MDE and the principles of optical lenses, we introduce LensAttack, a physical attack that involves strategically placing 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 begin by constructing a mathematical model of our attack, incorporating various attack parameters. Subsequently, we simulate the attack and evaluate its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models. The results highlight the significant impact of LensAttack on the accuracy of depth estimation in AD systems.

Optical Lens Attack on Deep Learning Based Monocular Depth Estimation

TL;DR

This paper introduces LensAttack, a physical attack that involves strategically placing optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths, and simulates the attack and evaluates its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models.

Abstract

Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a detected obstacle or changing lanes to avoid collision. In this paper, we investigate the security risks associated with monocular vision-based depth estimation algorithms utilized by AD systems. By exploiting the vulnerabilities of MDE and the principles of optical lenses, we introduce LensAttack, a physical attack that involves strategically placing 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 begin by constructing a mathematical model of our attack, incorporating various attack parameters. Subsequently, we simulate the attack and evaluate its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models. The results highlight the significant impact of LensAttack on the accuracy of depth estimation in AD systems.
Paper Structure (28 sections, 21 equations, 13 figures, 4 tables)

This paper contains 28 sections, 21 equations, 13 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Optical Principles for Lenses
  4. Monocular Depth Estimation
  5. Threat Model and Attack Scenario
  6. Threat Model
  7. Attack Scenario
  8. Optical Lens Attack
  9. Concave Lens Attack
  10. Convex Lens Attack
  11. Coverage of the Attack Lens
  12. Evaluation
  13. Attack Setup
  14. Target Models
  15. Evaluation Metrics
  16. ...and 13 more sections

Figures (13)

  • Figure 1: Ray diagrams of concave and convex lenses. (a)(b)(c) show the images formed by a convex lens, and (d) displays the images formed by a concave lens. The object is shown in red arrow and its corresponding image formed by the attack lens is shown in blue. $f$ represents the focal length.
  • Figure 2: $Lens Attack$ scenarios. AV1 to AV4 illustrate the concave lens attacks, and AV5 and AV6 showcase a convex lens attack.
  • Figure 3: Ray diagrams for (a) concave lens attack, and (b) first (c) second (d) third attack scenarios in convex lens attack. The left lens is the attack lens and the right dotted one stands for the monocular camera lens. The object is shown in red arrow and its corresponding image formed by the attack lens is shown in blue. $f$ represents the focal length of the attack lens.
  • Figure 4: Experimental setup for the AV and real-world driving.
  • Figure 5: Full image cropping with 0.8x and 0.6x cropping ratios.
  • ...and 8 more figures