Optical Lens Attack on Deep Learning Based Monocular Depth Estimation

TL;DR

This paper introduces LensAttack, a novel physical attack on monocular depth estimation in autonomous vehicles, using optical lenses to manipulate perceived depths and compromise system safety.

Contribution

It presents a new physical attack method exploiting optical lenses to deceive monocular depth estimation models in autonomous driving systems.

Findings

LensAttack significantly reduces depth estimation accuracy.

The attack is effective in simulated driving scenarios.

It demonstrates a real-world threat to vision-based autonomous systems.

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.