Potential Auto-driving Threat: Universal Rain-removal Attack

TL;DR

This paper introduces a universal rain-removal attack that exploits vulnerabilities in neural network-based rain-removal algorithms, significantly degrading their performance and revealing security concerns in autonomous driving perception systems under adverse weather.

Contribution

The study presents a novel non-additive spatial perturbation attack on rain-removal algorithms, highlighting security vulnerabilities and potential for real-world AI attack applications.

Findings

URA reduces scene restoration capability by 39.5%

URA decreases image quality by 26.4%

Effective against state-of-the-art rain-removal algorithms

Abstract

The problem of robustness in adverse weather conditions is considered a significant challenge for computer vision algorithms in the applicants of autonomous driving. Image rain removal algorithms are a general solution to this problem. They find a deep connection between raindrops/rain-streaks and images by mining the hidden features and restoring information about the rain-free environment based on the powerful representation capabilities of neural networks. However, previous research has focused on architecture innovations and has yet to consider the vulnerability issues that already exist in neural networks. This research gap hints at a potential security threat geared toward the intelligent perception of autonomous driving in the rain. In this paper, we propose a universal rain-removal attack (URA) on the vulnerability of image rain-removal algorithms by generating a non-additive spatial perturbation that significantly reduces the similarity and image quality of scene restoration. Notably, this perturbation is difficult to recognise by humans and is also the same for different target images. Thus, URA could be considered a critical tool for the vulnerability detection of image rain-removal algorithms. It also could be developed as a real-world artificial intelligence attack method. Experimental results show that URA can reduce the scene repair capability by 39.5% and the image generation quality by 26.4%, targeting the state-of-the-art (SOTA) single-image rain-removal algorithms currently available.