IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields

TL;DR

This paper introduces IPA-NeRF, a novel backdoor attack on Neural Radiance Fields that embeds hidden illusions, deceiving specific viewpoints without affecting overall performance, highlighting potential security vulnerabilities.

Contribution

We propose the first illusory poisoning attack on NeRF that embeds hidden backdoors, enabling targeted deception while maintaining normal functionality.

Findings

Successfully embeds backdoor views to produce illusions.

Maintains normal performance on standard inputs.

Achieves attack with minimal training set perturbations.

Abstract

Neural Radiance Field (NeRF) represents a significant advancement in computer vision, offering implicit neural network-based scene representation and novel view synthesis capabilities. Its applications span diverse fields including robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, etc., some of which are considered high-risk AI applications. However, despite its widespread adoption, the robustness and security of NeRF remain largely unexplored. In this study, we contribute to this area by introducing the Illusory Poisoning Attack against Neural Radiance Fields (IPA-NeRF). This attack involves embedding a hidden backdoor view into NeRF, allowing it to produce predetermined outputs, i.e. illusory, when presented with the specified backdoor view while maintaining normal performance with standard inputs. Our attack is specifically designed to deceive users or downstream models at a particular position while ensuring that any abnormalities in NeRF remain undetectable from other viewpoints. Experimental results demonstrate the effectiveness of our Illusory Poisoning Attack, successfully presenting the desired illusory on the specified viewpoint without impacting other views. Notably, we achieve this attack by introducing small perturbations solely to the training set. The code can be found at https://github.com/jiang-wenxiang/IPA-NeRF.