# Defeating Image Obfuscation with Deep Learning

arXiv: https://arxiv.org/abs/1609.00408 · HTML: https://mlsanity.com/paper/1609.00408/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2016.

## Built on by (most cited first, 30 of 43)

- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [Attribute-preserving Face Dataset Anonymization via Latent Code Optimization](https://mlsanity.com/paper/2303.11296/) (2023)
- [GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning](https://mlsanity.com/paper/2105.00529/) (2021)
- [Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability](https://mlsanity.com/paper/2210.08371/) (2022)
- [IdentityDP: Differential Private Identification Protection for Face Images](https://mlsanity.com/paper/2103.01745/) (2021)
- [DP-Image: Differential Privacy for Image Data in Feature Space](https://mlsanity.com/paper/2103.07073/) (2021)
- [Ethical Considerations for Responsible Data Curation](https://mlsanity.com/paper/2302.03629/) (2023)
- [Differentially Private Imaging via Latent Space Manipulation](https://mlsanity.com/paper/2103.05472/) (2021)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [Does Image Anonymization Impact Computer Vision Training?](https://mlsanity.com/paper/2306.05135/) (2023)
- [Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights](https://mlsanity.com/paper/2310.12462/) (2023)
- [LDP-Feat: Image Features with Local Differential Privacy](https://mlsanity.com/paper/2308.11223/) (2023)
- [A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directions](https://mlsanity.com/paper/2406.03820/) (2024)
- [A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective](https://mlsanity.com/paper/2311.16065/) (2023)
- [On Generating Identifiable Virtual Faces](https://mlsanity.com/paper/2110.07986/) (2021)
- [Temporally coherent video anonymization through GAN inpainting](https://mlsanity.com/paper/2106.02328/) (2021)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images](https://mlsanity.com/paper/2303.10435/) (2023)
- [Face Encryption via Frequency-Restricted Identity-Agnostic Attacks](https://mlsanity.com/paper/2308.05983/) (2023)
- [AdvCloak: Customized Adversarial Cloak for Privacy Protection](https://mlsanity.com/paper/2312.14407/) (2023)
- [Fantomas: Understanding Face Anonymization Reversibility](https://mlsanity.com/paper/2210.10651/) (2022)
- [Content-Aware Differential Privacy with Conditional Invertible Neural Networks](https://mlsanity.com/paper/2207.14625/) (2022)
- [Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection](https://mlsanity.com/paper/2208.10688/) (2022)
- [Multitask Identity-Aware Image Steganography via Minimax Optimization](https://mlsanity.com/paper/2107.05819/) (2021)
- [GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservation](https://mlsanity.com/paper/2201.03353/) (2022)
- [Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy](https://mlsanity.com/paper/2204.03559/) (2022)
- [StyleGAN as a Utility-Preserving Face De-identification Method](https://mlsanity.com/paper/2212.02611/) (2022)
- [Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos](https://mlsanity.com/paper/2601.11635/) (2026)
- [From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition](https://mlsanity.com/paper/2603.26336/) (2026)
- [Lossy Compression of Noisy Data for Private and Data-Efficient Learning](https://mlsanity.com/paper/2202.02892/) (2022)

## Abstract (arXiv)

We demonstrate that modern image recognition methods based on artificial neural networks can recover hidden information from images protected by various forms of obfuscation. The obfuscation techniques considered in this paper are mosaicing (also known as pixelation), blurring (as used by YouTube), and P3, a recently proposed system for privacy-preserving photo sharing that encrypts the significant JPEG coefficients to make images unrecognizable by humans. We empirically show how to train artificial neural networks to successfully identify faces and recognize objects and handwritten digits even if the images are protected using any of the above obfuscation techniques.