mlsanityData to 7 Oct 2026

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

arXiv 2403.17301 ↗First posted 26 Mar 2024cs.CV cs.CRcited by 32

Not on the map. Why?

Abstract (arXiv)

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patches, so they only affect a small, localized region in the MDE map but fail under various viewpoints. To address these limitations, we propose 3D Depth Fool (3D2Fool), the first 3D texture-based adversarial attack against MDE models. 3D2Fool is specifically optimized to generate 3D adversarial textures agnostic to model types of vehicles and to have improved robustness in bad weather conditions, such as rain and fog. Experimental results validate the superior performance of our 3D2Fool across various scenarios, including vehicles, MDE models, weather conditions, and viewpoints. Real-world experiments with printed 3D textures on physical vehicle models further demonstrate that our 3D2Fool can cause an MDE error of over 10 meters.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

30 of 44 references.

References · 30

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2017Adversarial Patchcited by 514
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  8. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  9. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  10. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  11. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  12. 2017Deep Photo Style Transfercited by 168
18 more
  1. 2019Self-Supervised Monocular Depth Hintscited by 127
  2. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  3. 2018TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agentscited by 111
  4. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  5. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  6. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 72
  7. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  8. 2020Rain rendering for evaluating and improving robustness to bad weathercited by 56
  9. 2022DTA: Physical Camouflage Attacks using Differentiable Transformation Networkcited by 51
  10. 2020Targeted Adversarial Perturbations for Monocular Depth Predictioncited by 40
  11. 2020Physical Adversarial Attack on Vehicle Detector in the Carla Simulatorcited by 38
  12. 2023ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasioncited by 31
  13. 2020Adversarial Patch Attacks on Monocular Depth Estimation Networkscited by 29
  14. 2023SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examplescited by 15
  15. 2023Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantizationcited by 14
  16. 2023SAAM: Stealthy Adversarial Attack on Monocular Depth Estimationcited by 12
  17. 2023APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigationcited by 10
  18. 2022Adversarial Attacks on Monocular Pose Estimationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 18; 2026: 7.

32 papers.

Sort:

By area:

  1. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Modelscited by 36
  2. 2025D3: Training-Free AI-Generated Video Detection Using Second-Order Featurescited by 32
  3. 2025Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projectorcited by 5
  4. 2024RenderBender: A Survey on Adversarial Attacks Using Differentiable Renderingcited by 3
  5. 2024BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimationcited by 2
  6. 2024Camouflaged Object Tracking: A Benchmarkcited by 2
  7. 2025Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insightscited by 2
  8. 2025ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimationcited by 2
  9. 2025Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systemscited by 2
  10. 2024Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectorscited by 1
  11. 2025Task-Agnostic Attacks Against Vision Foundation Modelscited by 1
  12. 2025Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarioscited by 1
20 more
  1. 2025A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detectioncited by 1
  2. 2026PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systemscited by 1
  3. 2024Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patchescited by 0
  4. 2024PADetBench: Towards Benchmarking Physical Attacks against Object Detectioncited by 0
  5. 2025Survey on Monocular Metric Depth Estimationcited by 0
  6. 2025LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deploymentcited by 0
  7. 2025BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical Worldcited by 0
  8. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  9. 2025Pixel-Optimization-Free Patch Attack on Stereo Depth Estimationcited by 0
  10. 2025ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflagescited by 0
  11. 2025BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splattingcited by 0
  12. 2025Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based propertiescited by 0
  13. 2025Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Drivingcited by 0
  14. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  15. 2026PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistencycited by 0
  16. 2026Sphere-Depth: A Benchmark for Depth Estimation Methods with Varying Spherical Camera Orientationscited by 0
  17. 2026Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Drivingcited by 0
  18. 2026Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detectioncited by 0
  19. 2026Scratched Lenses, Shifted Depth: Passive Camera-Side Optical Attackscited by 0
  20. 2026Adversarial Calibration Attack on Autonomous Vehiclescited by 0