Adversarial Geometry and Lighting using a Differentiable Renderer

By Hsueh-Ti Derek Liu, Michael Tao, Chun-Liang Li, Derek Nowrouzezahrai, Alec Jacobson. 2018

13 citations recorded by the source corpus.

Many machine learning classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Modern adversarial methods either directly alter pixel colors, or "paint" colors onto a 3D shapes. We propose novel adversarial attacks that directly alter the geometry of 3D objects and/or manipulate the lighting in a virtual scene. We leverage a novel differentiable renderer that is efficient to evaluate and analytically differentiate. Our renderer generates images realistic enough for correct classification by common pre-trained models, and we use it to design physical adversarial examples that consistently fool these models. We conduct qualitative and quantitate experiments to validate our adversarial geometry and adversarial lighting attack capabilities.

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects (2018, methodology): “[23] proposed a differentiable 3D renderer and used it to perturb both an object’s geometry and the scene’s lighting to cause a DNN to misbehave.”