Adversarial Attacks Using Differentiable Rendering: A Survey
Hull, Matthew, Zhang, Chao, Kira, Zsolt, Chau, Duen Horng
–arXiv.org Artificial Intelligence
Differentiable rendering methods have emerged as a promising means for generating photo-realistic and physically plausible adversarial attacks by manipulating 3D objects and scenes that can deceive deep neural networks (DNNs). Recently, differentiable rendering capabilities have evolved significantly into a diverse landscape of libraries, such as Mitsuba, PyTorch3D, and methods like Neural Radiance Fields and 3D Gaussian Splatting for solving inverse rendering problems that share conceptually similar properties commonly used to attack DNNs, such as back-propagation and optimization. However, the adversarial machine learning research community has not yet fully explored or understood such capabilities for generating attacks. Some key reasons are that researchers often have different attack goals, such as misclassification or misdetection, and use different tasks to accomplish these goals by manipulating different representation in a scene, such as the mesh or texture of an object. This survey adopts a task-oriented unifying framework that systematically summarizes common tasks, such as manipulating textures, altering illumination, and modifying 3D meshes to exploit vulnerabilities in DNNs. Our framework enables easy comparison of existing works, reveals research gaps and spotlights exciting future research directions in this rapidly evolving field. Through focusing on how these tasks enable attacks on various DNNs such as image classification, facial recognition, object detection, optical flow and depth estimation, our survey helps researchers and practitioners better understand the vulnerabilities of computer vision systems against photorealistic adversarial attacks that could threaten real-world applications.
arXiv.org Artificial Intelligence
Nov-14-2024
- Country:
- North America
- United States
- Nevada > Clark County
- Las Vegas (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Rhode Island > Providence County
- Providence (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Tennessee > Davidson County
- Nashville (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Washington > King County
- Seattle (0.04)
- Michigan > Wayne County
- Detroit (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.04)
- Santa Clara County > San Jose (0.04)
- Orange County > Anaheim (0.04)
- New York > New York County
- New York City (0.04)
- Nevada > Clark County
- Canada
- United States
- Europe
- Austria > Vienna (0.14)
- Switzerland (0.04)
- United Kingdom > Scotland
- City of Glasgow > Glasgow (0.04)
- France > Île-de-France
- Asia
- Middle East > Oman (0.04)
- South Korea > Seoul
- Seoul (0.04)
- North America
- Genre:
- Overview (1.00)
- Research Report (0.82)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Government > Military (1.00)
- Transportation > Ground
- Road (0.68)
- Technology: