mlsanityData to 14 Oct 2026

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

arXiv 2308.03108 ↗First posted 6 Aug 2023cs.CV cs.CRcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel underlineStealthy underlineAdversarial underlineAttacks on underlineMDE (SAAM) that compromises MDE by either corrupting the estimated distance or causing an object to seamlessly blend into its surroundings. Our experiments, demonstrate that the designed stealthy patch successfully causes a DNN-based MDE to misestimate the depth of objects. In fact, our proposed adversarial patch achieves a significant 60% depth error with 99% ratio of the affected region. Importantly, despite its adversarial nature, the patch maintains a naturalistic appearance, making it inconspicuous to human observers. We believe that this work sheds light on the threat of adversarial attacks in the context of MDE on edge devices. We hope it raises awareness within the community about the potential real-life harm of such attacks and encourages further research into developing more robust and adaptive defense mechanisms.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 6 Aug 2023.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  8. 2016Universal adversarial perturbationscited by 784
  9. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  10. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  11. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  12. 2014Understanding Deep Image Representations by Inverting Themcited by 403
17 more
  1. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  2. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  3. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  4. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  5. 2020MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Cameracited by 59
  6. 2022Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepthcited by 58
  7. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  8. 2016Simple Black-Box Adversarial Perturbations for Deep Networkscited by 42
  9. 2023DAP: A Dynamic Adversarial Patch for Evading Person Detectorscited by 40
  10. 2019Defending against Whitebox Adversarial Attacks via Randomized Discretizationcited by 29
  11. 2020Adversarial Patch Attacks on Monocular Depth Estimation Networkscited by 29
  12. 2020LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalizationcited by 28
  13. 2023AdvART: Adversarial Art for Camouflaged Object Detection Attackscited by 12
  14. 2023APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigationcited by 10
  15. 2021The art of defense: letting networks fool the attackercited by 6
  16. 2022ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraintscited by 5
  17. 2022Image Masking for Robust Self-Supervised Monocular Depth Estimationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6; 2025: 5.

12 papers.

  1. 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Drivingcited by 32
  2. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  3. 2024Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attackscited by 6
  4. 2024SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applicationscited by 4
  5. 2024Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehiclescited by 3
  6. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  7. 2025Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attackscited by 1
  8. 2024Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patchescited by 0
  9. 2024Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attackcited by 0
  10. 2025BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical Worldcited by 0
  11. 2025Pixel-Optimization-Free Patch Attack on Stereo Depth Estimationcited by 0
  12. 2025BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splattingcited by 0