Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects

TL;DR

This paper demonstrates how to create transferable adversarial 3D objects by altering textures, exposing vulnerabilities in machine learning models within virtual environments using accessible tools.

Contribution

It introduces a method for crafting adversarial 3D objects through texture modifications using surrogate renderers, enabling transferability to advanced engines.

Findings

Adversarial textures can fool neural classifiers in 3D environments.

Simple tools and surrogate renderers suffice for creating effective adversarial objects.

The proposed saliency-based attack improves transferability across rendering engines.

Abstract

In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds. On one hand, these environments could also become a mean to study the weaknesses of Machine Learning algorithms, or to simulate training settings that allow Machine Learning models to gain robustness to 3D adversarial attacks. On the other hand, their growing popularity might also attract those that aim at creating adversarial conditions to invalidate the benchmarking process, especially in the case of public environments that allow the contribution from a large community of people. Most of the existing Adversarial Machine Learning approaches are focused on static images, and little work has been done in studying how to deal with 3D environments and how a 3D object should be altered to fool a classifier that observes it. In this paper, we study how to craft adversarial 3D objects by altering their textures, using a tool chain composed of easily accessible elements. We show that it is possible, and indeed simple, to create adversarial objects using off-the-shelf limited surrogate renderers that can compute gradients with respect to the parameters of the rendering process, and, to a certain extent, to transfer the attacks to more advanced 3D engines. We propose a saliency-based attack that intersects the two classes of renderers in order to focus the alteration to those texture elements that are estimated to be effective in the target engine, evaluating its impact in popular neural classifiers.