Restoring Gaussian Blurred Face Images for Deanonymization Attacks

TL;DR

This paper introduces Revelio, a novel deblurring method that effectively restores highly blurred face images using generative models, raising concerns about the reliability of Gaussian blur for privacy protection.

Contribution

Revelio leverages a generative model's memorization effect and combines diffusion-based deblurring with identity retrieval to improve face restoration under high-blur conditions.

Findings

Achieves 95.9% re-identification accuracy on blurred faces

Outperforms existing deblurring methods in high-blur scenarios

Demonstrates Gaussian blur's inadequacy for face anonymization

Abstract

Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this question by developing a deblurring method called Revelio. The key intuition is to leverage a generative model's memorization effect and approximate the inverse function of Gaussian blur for face restoration. Compared with existing methods, we design the deblurring process to be identity-preserving. It uses a conditional Diffusion model for preliminary face restoration and then uses an identity retrieval model to retrieve related images to further enhance fidelity. We evaluate Revelio with large public face image datasets and show that it can effectively restore blurred faces, especially under a high-blurring setting. It has a re-identification accuracy of 95.9%, outperforming existing solutions. The result suggests that Gaussian blur should not be used for face anonymization purposes. We also demonstrate the robustness of this method against mismatched Gaussian kernel sizes and functions, and test preliminary countermeasures and adaptive attacks to inspire future work.