mlsanityData to 14 Oct 2026

Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks

arXiv 2406.05857 ↗First posted 9 Jun 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L_0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 9 Jun 2024.

Builds on

59 of 74 references.

References · 59

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  12. 2019Contrastive Multiview Codingcited by 1,301
38 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  3. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  4. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  5. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  6. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  7. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  8. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  9. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  10. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 232
  11. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  12. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  13. 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
  14. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  15. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  16. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
  17. 2020Adversarial Self-Supervised Contrastive Learningcited by 139
  18. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  19. 2019Self-Supervised Monocular Depth Hintscited by 127
  20. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  21. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  22. 2020Contrastive Learning with Adversarial Examplescited by 91
  23. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  24. 2020MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Cameracited by 59
  25. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  26. 2019Towards Adversarially Robust Object Detectioncited by 55
  27. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  28. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  29. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  30. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  31. 2020Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Predictioncited by 41
  32. 2020Targeted Adversarial Perturbations for Monocular Depth Predictioncited by 40
  33. 2020Learning Monocular Visual Odometry via Self-Supervised Long-Term Modelingcited by 39
  34. 2020Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentationcited by 38
  35. 2021Adversarial Training Helps Transfer Learning via Better Representationscited by 36
  36. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  37. 2023TransFlow: Transformer as Flow Learnercited by 32
  38. 2019APRICOT: A Dataset of Physical Adversarial Attacks on Object Detectioncited by 31

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 73
  2. 2025Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimationcited by 6
  3. 2025Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attackscited by 1
  4. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  5. 2025Monocular Depth Estimation with Global-Aware Discretization and Local Context Modelingcited by 0