# PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval

arXiv: https://arxiv.org/abs/2102.10802 · HTML: https://mlsanity.com/paper/2102.10802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [A Decade Survey of Content Based Image Retrieval using Deep Learning](https://mlsanity.com/paper/2012.00641/) (2020)
- [Towards Demystifying Membership Inference Attacks](https://mlsanity.com/paper/1807.09173/) (2018)
- [Privacy Preserving Face Recognition Utilizing Differential Privacy](https://mlsanity.com/paper/2005.10486/) (2020)
- [Recent Advance in Content-based Image Retrieval: A Literature Survey](https://mlsanity.com/paper/1706.06064/) (2017)
- [Combination of Multiple Global Descriptors for Image Retrieval](https://mlsanity.com/paper/1903.10663/) (2019)
- [Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers](https://mlsanity.com/paper/2006.14576/) (2020)
- [Privacy-Aware Eye Tracking Using Differential Privacy](https://mlsanity.com/paper/1812.08000/) (2018)
- [A study of the classification of low-dimensional data with supervised manifold learning](https://mlsanity.com/paper/1507.05880/) (2015)
- [Supervised Dimensionality Reduction via Distance Correlation Maximization](https://mlsanity.com/paper/1601.00236/) (2016)
- [NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks](https://mlsanity.com/paper/1808.04580/) (2018)
- [Randomness Efficient Fast-Johnson-Lindenstrauss Transform with Applications in Differential Privacy and Compressed Sensing](https://mlsanity.com/paper/1410.2470/) (2014)
- [Secure k-Nearest Neighbor Query over Encrypted Data in Outsourced Environments](https://mlsanity.com/paper/1307.4824/) (2013)
- [MM Algorithms for Variance Components Models](https://mlsanity.com/paper/1509.07426/) (2015)

## Abstract (arXiv)

Differential Privacy offers strong guarantees such as immutable privacy under post processing. Thus it is often looked to as a solution to learning on scattered and isolated data. This work focuses on supervised manifold learning, a paradigm that can generate fine-tuned manifolds for a target use case. Our contributions are two fold. 1) We present a novel differentially private method textitPrivateMail for supervised manifold learning, the first of its kind to our knowledge. 2) We provide a novel private geometric embedding scheme for our experimental use case. We experiment on private "content based image retrieval" - embedding and querying the nearest neighbors of images in a private manner - and show extensive privacy-utility tradeoff results, as well as the computational efficiency and practicality of our methods.