Projection-Based Adversarial Attack Using Physics-in-the-Loop Optimization for Monocular Depth Estimation

Kusakabe, Takeru

doi:10.1587/transinf.2025MUL0002

Projection-Based Adversarial Attack Using Physics-in-the-Loop Optimization for Monocular Depth Estimation

2026-04-01

0

PRE

AI

DOI：10.1587/transinf.2025MUL0002

Original

Original request for help

Save

Abstract

En 中文

Deep neural networks (DNNs) remain vulnerable to adversarial attacks that cause misclassification when specific perturbations are added to input images. This vulnerability also threatens the reliability of DNN-based monocular depth estimation (MDE) models, making robustness enhancement a critical need in practical applications. To validate the vulnerability of DNN-based MDE models, this study proposes a projection-based adversarial attack method that projects perturbation light onto a target object. The proposed method employs physics-in-the-loop (PITL) optimization- evaluating candidate solutions in actual environments to account for device specifications and disturbances-and utilizes a separable covariance matrix adaptation evolution strategy. Experiments confirmed that the proposed method successfully created adversarial examples that lead to depth misestimations, resulting in parts of objects disappearing from the target scene.

Keywords:

adversarial examples

monocular depth estimation

physical attack

physics-in-the-loop

Projection-Based Adversarial Attack Using Physics-in-the-Loop Optimization for Monocular Depth Estimation

Abstract

Journal

Organization