Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patches
Not on the map. Why?
Abstract (arXiv)
Adversarial attacks against monocular depth estimation (MDE) systems pose significant challenges, particularly in safety-critical applications such as autonomous driving. Existing patch-based adversarial attacks for MDE are confined to the vicinity of the patch, making it difficult to affect the entire target. To address this limitation, we propose a physics-based adversarial attack on monocular depth estimation, employing a framework called Attack with Shape-Varying Patches (ASP), aiming to optimize patch content, shape, and position to maximize effectiveness. We introduce various mask shapes, including quadrilateral, rectangular, and circular masks, to enhance the flexibility and efficiency of the attack. Furthermore, we propose a new loss function to extend the influence of the patch beyond the overlapping regions. Experimental results demonstrate that our attack method generates an average depth error of 18 meters on the target car with a patch area of 1/9, affecting over 98% of the target area.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 58 references that are in the map. First posted on arXiv 24 Jul 2024.
Builds on
30 of 58 references.
References · 30
- 2013Intriguing properties of neural networkscited by 5,114
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
- 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2016A study of the effect of JPG compression on adversarial imagescited by 196
- 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
- 2018Physical Adversarial Examples for Object Detectorscited by 163
- 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
- 2019Self-Supervised Monocular Depth Hintscited by 127
- 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
- 2019SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editingcited by 93
- 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
18 more
- 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 62
- 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
- 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
- 2020Bidirectional Attention Network for Monocular Depth Estimationcited by 48
- 2020Targeted Adversarial Perturbations for Monocular Depth Predictioncited by 40
- 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Drivingcited by 32
- 2019Defending against Whitebox Adversarial Attacks via Randomized Discretizationcited by 29
- 2020Adversarial Patch Attacks on Monocular Depth Estimation Networkscited by 29
- 2023Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical Worldcited by 21
- 2020Adversarial Attacks on Monocular Depth Estimationcited by 20
- 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
- 2019Deep Robust Single Image Depth Estimation Neural Network Using Scene Understandingcited by 15
- 2023SAAM: Stealthy Adversarial Attack on Monocular Depth Estimationcited by 12
- 2023APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigationcited by 10
- 2018Drone Detection Using Depth Mapscited by 8
- 2024Flexible Physical Camouflage Generation Based on a Differential Approachcited by 7
- 2023DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generationcited by 5
- 2020Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimizationcited by 3
Built on by
Not cited yet.