# LDP-Feat: Image Features with Local Differential Privacy

arXiv: https://arxiv.org/abs/2308.11223 · HTML: https://mlsanity.com/paper/2308.11223/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 53 references that are in the map.
- First posted on arXiv 22 Aug 2023.

## Builds on (most cited first, 26 of 26)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Examining the Impact of Blur on Recognition by Convolutional Networks](https://mlsanity.com/paper/1611.05760/) (2016)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Privacy Preserving Image-Based Localization](https://mlsanity.com/paper/1903.05572/) (2019)
- [Defeating Image Obfuscation with Deep Learning](https://mlsanity.com/paper/1609.00408/) (2016)
- [Local Descriptors Optimized for Average Precision](https://mlsanity.com/paper/1804.05312/) (2018)
- [Local Differential Privacy and Its Applications: A Comprehensive Survey](https://mlsanity.com/paper/2008.03686/) (2020)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Differential Privacy: An Economic Method for Choosing Epsilon](https://mlsanity.com/paper/1402.3329/) (2014)
- [Learning Privacy Preserving Encodings through Adversarial Training](https://mlsanity.com/paper/1802.05214/) (2018)
- [A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis](https://mlsanity.com/paper/2010.05253/) (2020)
- [Differential Privacy Techniques for Cyber Physical Systems: A Survey](https://mlsanity.com/paper/1812.02282/) (2018)
- [NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning](https://mlsanity.com/paper/2112.12785/) (2021)
- [How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines](https://mlsanity.com/paper/2103.05086/) (2021)
- [Privacy Preserving Visual SLAM](https://mlsanity.com/paper/2007.10361/) (2020)
- [Image Reconstruction from Bag-of-Visual-Words](https://mlsanity.com/paper/1505.05190/) (2015)
- [Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset](https://mlsanity.com/paper/1906.05675/) (2019)

## Built on by (most cited first, 10 of 10)

- [Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization](https://mlsanity.com/paper/2507.23569/) (2025)
- [Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations](https://mlsanity.com/paper/2407.14367/) (2024)
- [Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Information](https://mlsanity.com/paper/2409.11536/) (2024)
- [LeakyCLIP: Extracting Training Data from CLIP](https://mlsanity.com/paper/2508.00756/) (2025)
- [LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing](https://mlsanity.com/paper/2603.03711/) (2026)
- [Calibrating Practical Privacy Risks for Differentially Private Machine Learning](https://mlsanity.com/paper/2410.22673/) (2024)
- [Privacy-Preserving Structureless Visual Localization via Image Obfuscation](https://mlsanity.com/paper/2604.12068/) (2026)
- [Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization](https://mlsanity.com/paper/2604.22310/) (2026)
- [Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression](https://mlsanity.com/paper/2606.31164/) (2026)
- [Misanthrope: A Privacy-Preserving Keypoint Detector](https://mlsanity.com/paper/2608.23012/) (2026)

## Abstract (arXiv)

Modern computer vision services often require users to share raw feature descriptors with an untrusted server. This presents an inherent privacy risk, as raw descriptors may be used to recover the source images from which they were extracted. To address this issue, researchers recently proposed privatizing image features by embedding them within an affine subspace containing the original feature as well as adversarial feature samples. In this paper, we propose two novel inversion attacks to show that it is possible to (approximately) recover the original image features from these embeddings, allowing us to recover privacy-critical image content. In light of such successes and the lack of theoretical privacy guarantees afforded by existing visual privacy methods, we further propose the first method to privatize image features via local differential privacy, which, unlike prior approaches, provides a guaranteed bound for privacy leakage regardless of the strength of the attacks. In addition, our method yields strong performance in visual localization as a downstream task while enjoying the privacy guarantee.