Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?

TL;DR

This paper evaluates the robustness of pixel-level protective perturbations in portrait privacy defense methods under real-world image transformations, revealing their vulnerability and proposing a purification framework to mitigate this issue.

Contribution

It systematically assesses existing proactive defenses against common image transformations and introduces a purification method to remove protective perturbations effectively.

Findings

Pixel-level perturbation defenses often fail under real-world transformations.

Transformations like scaling and color compression can nullify protective perturbations.

The proposed purification framework can efficiently remove perturbations with low computational cost.

Abstract

Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have already attracted increasing attention for privacy protection. In real-world scenarios, images inevitably undergo various transformations during cross-device display and dissemination--such as scale transformations and color compression--that directly alter pixel values. However, it remains unclear whether such pixel-level modifications affect the effectiveness of existing proactive defense methods that rely on pixel-level perturbations. To solve this problem, we conduct a systematic evaluation of representative proactive defenses under image transformation. The evaluated methods are selected to span different generation architectures such as diffusion and GAN-based models, as well as defense scopes covering both portrait and natural images, and are assessed using both qualitative and quantitative metrics for subjective and objective comparison. Experimental results indicate that defense methods based on pixel-level perturbations struggle to withstand common image transformations, posing a risk of defense failure in real-world applications. To further highlight this risk, we propose a simple yet effective purification framework by leveraging the vulnerabilities induced by real-world image transformations. Experimental results demonstrate that the proposed method can efficiently remove protective perturbations with low computational cost, highlighting previously overlooked risks to the research community.