UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Phute, Mansi, Hull, Matthew, Wang, Haoran, Helbling, Alec, Peng, ShengYun, Lunardi, Willian, Andreoni, Martin, Lee, Wenke, Chau, Duen Horng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917044468842496
author Phute, Mansi
Hull, Matthew
Wang, Haoran
Helbling, Alec
Peng, ShengYun
Lunardi, Willian
Andreoni, Martin
Lee, Wenke
Chau, Duen Horng
author_facet Phute, Mansi
Hull, Matthew
Wang, Haoran
Helbling, Alec
Peng, ShengYun
Lunardi, Willian
Andreoni, Martin
Lee, Wenke
Chau, Duen Horng
contents Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions. However, these simulations are non-differentiable, forcing researchers to create attacks that do not integrate simulation environmental factors, reducing attack success. To address this limitation, we introduce UNDREAM, the first software framework that bridges the gap between photorealistic simulators and differentiable renderers to enable end-to-end optimization of adversarial perturbations on any 3D objects. UNDREAM enables manipulation of the environment by offering complete control over weather, lighting, backgrounds, camera angles, trajectories, and realistic human and object movements, thereby allowing the creation of diverse scenes. We showcase a wide array of distinct physically plausible adversarial objects that UNDREAM enables researchers to swiftly explore in different configurable environments. This combination of photorealistic simulation and differentiable optimization opens new avenues for advancing research of physical adversarial attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Phute, Mansi
Hull, Matthew
Wang, Haoran
Helbling, Alec
Peng, ShengYun
Lunardi, Willian
Andreoni, Martin
Lee, Wenke
Chau, Duen Horng
Cryptography and Security
Artificial Intelligence
Machine Learning
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions. However, these simulations are non-differentiable, forcing researchers to create attacks that do not integrate simulation environmental factors, reducing attack success. To address this limitation, we introduce UNDREAM, the first software framework that bridges the gap between photorealistic simulators and differentiable renderers to enable end-to-end optimization of adversarial perturbations on any 3D objects. UNDREAM enables manipulation of the environment by offering complete control over weather, lighting, backgrounds, camera angles, trajectories, and realistic human and object movements, thereby allowing the creation of diverse scenes. We showcase a wide array of distinct physically plausible adversarial objects that UNDREAM enables researchers to swiftly explore in different configurable environments. This combination of photorealistic simulation and differentiable optimization opens new avenues for advancing research of physical adversarial attacks.
title UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.16923