BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

TL;DR

BlurGuard introduces a simple yet effective adaptive blurring technique to make adversarial image protections against AI editing more robust and less reversible, enhancing security without compromising image quality.

Contribution

It proposes an adaptive Gaussian blur method that significantly improves the irreversibility and robustness of adversarial noise for image protection against editing.

Findings

Enhances protection against reversal techniques across diverse scenarios.

Reduces perceptual quality degradation of protected images.

Consistently outperforms existing methods in robustness tests.

Abstract

Recent advances in text-to-image models have increased the exposure of powerful image editing techniques as a tool, raising concerns about their potential for malicious use. An emerging line of research to address such threats focuses on implanting "protective" adversarial noise into images before their public release, so future attempts to edit them using text-to-image models can be impeded. However, subsequent works have shown that these adversarial noises are often easily "reversed," e.g., with techniques as simple as JPEG compression, casting doubt on the practicality of the approach. In this paper, we argue that adversarial noise for image protection should not only be imperceptible, as has been a primary focus of prior work, but also irreversible, viz., it should be difficult to detect as noise provided that the original image is hidden. We propose a surprisingly simple method to enhance the robustness of image protection methods against noise reversal techniques. Specifically, it applies an adaptive per-region Gaussian blur on the noise to adjust the overall frequency spectrum. Through extensive experiments, we show that our method consistently improves the per-sample worst-case protection performance of existing methods against a wide range of reversal techniques on diverse image editing scenarios, while also reducing quality degradation due to noise in terms of perceptual metrics. Code is available at https://github.com/jsu-kim/BlurGuard.