DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
arXiv:2104.02655
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.
References in corpus (10)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Robustness May Be at Odds with Accuracy
- Fader Networks: Manipulating Images by Sliding Attributes
- Defeating Image Obfuscation with Deep Learning
- FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis
- Latent Space Non-Linear Statistics
- A Utility-Preserving GAN for Face Obscuration
- Differentially Private Imaging via Latent Space Manipulation
- Deep Learning-based Face Super-Resolution: A Survey