DeepBlur: A Simple and Effective Method for Natural Image Obfuscation

TL;DR

DeepBlur is a novel image obfuscation technique that uses latent space blurring in generative models to effectively protect privacy while maintaining high image quality and computational efficiency.

Contribution

We introduce DeepBlur, a simple and effective latent space blurring method for image obfuscation that outperforms existing techniques in quality and security.

Findings

Produces high-quality obfuscated images

Outperforms existing methods in defense strength

Efficient and practical for real-world use

Abstract

There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software. However, established image obfuscation techniques are either vulnerable to re-identification attacks by human or deep learning models, insufficient in preserving image fidelity, or too computationally intensive to be practical. To tackle these issues, we present DeepBlur, a simple yet effective method for image obfuscation by blurring in the latent space of an unconditionally pre-trained generative model that is able to synthesize photo-realistic facial images. We compare it with existing methods by efficiency and image quality, and evaluate against both state-of-the-art deep learning models and industrial products (e.g., Face++, Microsoft face service). Experiments show that our method produces high quality outputs and is the strongest defense for most test cases.