# DeepBlur: A Simple and Effective Method for Natural Image Obfuscation

arXiv: https://arxiv.org/abs/2104.02655 · HTML: https://mlsanity.com/paper/2104.02655/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [Latent Space Oddity: on the Curvature of Deep Generative Models](https://mlsanity.com/paper/1710.11379/) (2017)
- [Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors](https://mlsanity.com/paper/1910.14667/) (2019)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Deep Feature Interpolation for Image Content Changes](https://mlsanity.com/paper/1611.05507/) (2016)
- [Towards Open-Set Identity Preserving Face Synthesis](https://mlsanity.com/paper/1803.11182/) (2018)
- [Metrics for Deep Generative Models](https://mlsanity.com/paper/1711.01204/) (2017)
- [AnonymousNet: Natural Face De-Identification with Measurable Privacy](https://mlsanity.com/paper/1904.12620/) (2019)
- [Defeating Image Obfuscation with Deep Learning](https://mlsanity.com/paper/1609.00408/) (2016)
- [A Hybrid Model for Identity Obfuscation by Face Replacement](https://mlsanity.com/paper/1804.04779/) (2018)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Semantically Decomposing the Latent Spaces of Generative Adversarial Networks](https://mlsanity.com/paper/1705.07904/) (2017)
- [Privacy-preserving Machine Learning through Data Obfuscation](https://mlsanity.com/paper/1807.01860/) (2018)
- [Privacy-Protective-GAN for Face De-identification](https://mlsanity.com/paper/1806.08906/) (2018)
- [FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis](https://mlsanity.com/paper/1812.01288/) (2018)
- [Component Attention Guided Face Super-Resolution Network: CAGFace](https://mlsanity.com/paper/1910.08761/) (2019)
- [Differentially Private Imaging via Latent Space Manipulation](https://mlsanity.com/paper/2103.05472/) (2021)

## Built on by (most cited first, 13 of 13)

- [CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search](https://mlsanity.com/paper/2306.10008/) (2023)
- [SoK: Anti-Facial Recognition Technology](https://mlsanity.com/paper/2112.04558/) (2021)
- [Face De-identification: State-of-the-art Methods and Comparative Studies](https://mlsanity.com/paper/2411.09863/) (2024)
- [On Generating Identifiable Virtual Faces](https://mlsanity.com/paper/2110.07986/) (2021)
- [Addressing Privacy Threats from Machine Learning](https://mlsanity.com/paper/2111.04439/) (2021)
- [Synthetic Dataset Generation for Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2210.03205/) (2022)
- [A Key-Driven Framework for Identity-Preserving Face Anonymization](https://mlsanity.com/paper/2409.03434/) (2024)
- [FaceAnonyMixer: Cancelable Faces via Identity Consistent Latent Space Mixing](https://mlsanity.com/paper/2508.05636/) (2025)
- [Privacy-Preserving Medical Image Classification through Deep Learning and Matrix Decomposition](https://mlsanity.com/paper/2308.16530/) (2023)
- [Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation](https://mlsanity.com/paper/2409.08301/) (2024)
- [Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance](https://mlsanity.com/paper/2410.18717/) (2024)
- [On the Importance of Conditioning for Privacy-Preserving Data Augmentation](https://mlsanity.com/paper/2504.05849/) (2025)
- [Bit-ViP: Leveraging Bit-planes to Preserve Visual Privacy in Images through Obfuscation](https://mlsanity.com/paper/2606.29417/) (2026)

## Abstract (arXiv)

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.