# Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inverse

arXiv: https://arxiv.org/abs/2202.08309 · HTML: https://mlsanity.com/paper/2202.08309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 22 of 22)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping](https://mlsanity.com/paper/1912.13457/) (2019)
- [Natural and Effective Obfuscation by Head Inpainting](https://mlsanity.com/paper/1711.09001/) (2017)
- [RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes](https://mlsanity.com/paper/1908.07269/) (2019)
- [A Hybrid Model for Identity Obfuscation by Face Replacement](https://mlsanity.com/paper/1804.04779/) (2018)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [Make a Face: Towards Arbitrary High Fidelity Face Manipulation](https://mlsanity.com/paper/1908.07191/) (2019)
- [DP-Image: Differential Privacy for Image Data in Feature Space](https://mlsanity.com/paper/2103.07073/) (2021)
- [Differential Privacy Techniques for Cyber Physical Systems: A Survey](https://mlsanity.com/paper/1812.02282/) (2018)
- [Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics](https://mlsanity.com/paper/2104.01753/) (2021)
- [P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification](https://mlsanity.com/paper/1905.12883/) (2019)
- [Differentially Private Imaging via Latent Space Manipulation](https://mlsanity.com/paper/2103.05472/) (2021)
- [FReeNet: Multi-Identity Face Reenactment](https://mlsanity.com/paper/1905.11805/) (2019)
- [Topology-aware Differential Privacy for Decentralized Image Classification](https://mlsanity.com/paper/2006.07817/) (2020)
- [Differentially Private Distributed Data Summarization under Covariate Shift](https://mlsanity.com/paper/1910.12832/) (2019)
- [Improved Supervised Training of Physics-Guided Deep Learning Image Reconstruction with Multi-Masking](https://mlsanity.com/paper/2010.13868/) (2020)
- [Deciding Accuracy of Differential Privacy Schemes](https://mlsanity.com/paper/2011.06404/) (2020)
- [Applications of Differential Privacy in Social Network Analysis: A Survey](https://mlsanity.com/paper/2010.02973/) (2020)
- [Differential Privacy in Cognitive Radio Networks: A Comprehensive Survey](https://mlsanity.com/paper/2111.02011/) (2021)

## Abstract (arXiv)

Differential privacy (DP) has been the de-facto standard to preserve privacy-sensitive information in database. Nevertheless, there lacks a clear and convincing contextualization of DP in image database, where individual images' indistinguishable contribution to a certain analysis can be achieved and observed when DP is exerted. As a result, the privacy-accuracy trade-off due to integrating DP is insufficiently demonstrated in the context of differentially-private image database. This work aims at contextualizing DP in image database by an explicit and intuitive demonstration of integrating conceptional differential privacy with images. To this end, we design a lightweight approach dedicating to privatizing image database as a whole and preserving the statistical semantics of the image database to an adjustable level, while making individual images' contribution to such statistics indistinguishable. The designed approach leverages principle component analysis (PCA) to reduce the raw image with large amount of attributes to a lower dimensional space whereby DP is performed, so as to decrease the DP load of calculating sensitivity attribute-by-attribute. The DP-exerted image data, which is not visible in its privatized format, is visualized through PCA inverse such that both a human and machine inspector can evaluate the privatization and quantify the privacy-accuracy trade-off in an analysis on the privatized image database. Using the devised approach, we demonstrate the contextualization of DP in images by two use cases based on deep learning models, where we show the indistinguishability of individual images induced by DP and the privatized images' retention of statistical semantics in deep learning tasks, which is elaborated by quantitative analyses on the privacy-accuracy trade-off under different privatization settings.