RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering

Hull, Matthew; Wang, Haoran; Lau, Matthew; Helbling, Alec; Phute, Mansi; Zhang, Chao; Kira, Zsolt; Lunardi, Willian; Andreoni, Martin; Lee, Wenke; Chau, Duen Horng

doi:10.24963/ijcai.2025/1163

RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering

Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling, Mansi Phute, Chao Zhang, Zsolt Kira, Willian Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Survey Track. Pages 10473-10480.

https://doi.org/10.24963/ijcai.2025/1163

Keywords

Computer Vision: CV: Adversarial learning, adversarial attack and defense methods
Machine Learning: ML: Adversarial machine learning
Computer Vision: CV: Machine learning for vision
Computer Vision: CV: 3D computer vision

Abstract

Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Their ability to produce both physically plausible and differentiable models of scenes are key ingredient needed to produce physically plausible adversarial attacks on DNNs. However, the adversarial machine learning community has yet to fully explore these capabilities, partly due to differing attack goals (e.g., misclassification, misdetection) and a wide range of possible scene manipulations used to achieve them (e.g., alter texture, mesh). This survey contributes a framework that unifies diverse goals and tasks, facilitating easy comparison of existing work, identifying research gaps, and highlighting future directions—ranging from expanding attack goals and tasks to account for new modalities, state-of-the-art models, tools, and pipelines, to underscoring the importance of studying real-world threats in complex scenes.

Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling, Mansi Phute, Chao Zhang, Zsolt Kira, Willian Lunardi, Martin Andreoni, Wenke Lee, and Duen Horng Chau. 2025. RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10473–10480. https://doi.org/10.24963/ijcai.2025/1163

@inproceedings{ijcai2025p1163,
  title     = {RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering},
  author    = {Hull, Matthew and Wang, Haoran and Lau, Matthew and Helbling, Alec and Phute, Mansi and Zhang, Chao and Kira, Zsolt and Lunardi, Willian and Andreoni, Martin and Lee, Wenke and Chau, Duen Horng},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10473--10480},
  year      = {2025},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2025/1163},
  url       = {https://doi.org/10.24963/ijcai.2025/1163},
}

TY  - CPAPER
TI  - RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering
AU  - Hull, Matthew
AU  - Wang, Haoran
AU  - Lau, Matthew
AU  - Helbling, Alec
AU  - Phute, Mansi
AU  - Zhang, Chao
AU  - Kira, Zsolt
AU  - Lunardi, Willian
AU  - Andreoni, Martin
AU  - Lee, Wenke
AU  - Chau, Duen Horng
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10473
EP  - 10480
DO  - 10.24963/ijcai.2025/1163
UR  - https://doi.org/10.24963/ijcai.2025/1163
ER  -