mlsanityData to 7 Oct 2026

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields

arXiv 2310.03578 ↗First posted 5 Oct 2023cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRFs) have recently emerged as a powerful tool for 3D scene representation and rendering. These data-driven models can learn to synthesize high-quality images from sparse 2D observations, enabling realistic and interactive scene reconstructions. However, the growing usage of NeRFs in critical applications such as augmented reality, robotics, and virtual environments could be threatened by adversarial attacks. In this paper we present how generalizable NeRFs can be attacked by both low-intensity adversarial attacks and adversarial patches, where the later could be robust enough to be used in real world applications. We also demonstrate targeted attacks, where a specific, predefined output scene is generated by these attack with success.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 5 Oct 2023.

Builds on

36 of 44 references.

References · 36

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  8. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  9. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  11. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  12. 2017Adversarial Patchcited by 514
24 more
  1. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  2. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  3. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  4. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  5. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  6. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  7. 2021Vision-Only Robot Navigation in a Neural Radiance Worldcited by 153
  8. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  9. 2021NeRF for Outdoor Scene Relightingcited by 114
  10. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  11. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  12. 2021FoV-NeRF: Foveated Neural Radiance Fields for Virtual Realitycited by 79
  13. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  14. 2022Loc-NeRF: Monte Carlo Localization using Neural Radiance Fieldscited by 69
  15. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  16. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  17. 2022Compressing Explicit Voxel Grid Representations: fast NeRFs become also smallcited by 48
  18. 2017Synthesizing Robust Adversarial Examplescited by 39
  19. 2016Adversarial Diversity and Hard Positive Generationcited by 35
  20. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  21. 2022Points2NeRF: Generating Neural Radiance Fields from 3D point cloudcited by 11
  22. 2023NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbationscited by 10
  23. 2023NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigationcited by 8
  24. 2023Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Designcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 4.

10 papers.

  1. 2024Poison-splat: Computation Cost Attack on 3D Gaussian Splattingcited by 17
  2. 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Imagescited by 15
  3. 2025StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusionscited by 6
  4. 2024IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fieldscited by 5
  5. 2024Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noisecited by 4
  6. 2026Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splattingcited by 1
  7. 2026PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systemscited by 1
  8. 2025Mesters'eges Intelligencia Kutat'asok Magyarorsz'agoncited by 0
  9. 20263D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanismcited by 0
  10. 2026Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformercited by 0