# When Differential Privacy Meets Interpretability: A Case Study

arXiv: https://arxiv.org/abs/2106.13203 · HTML: https://mlsanity.com/paper/2106.13203/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Differentially Private Learning Needs Better Features (or Much More Data)](https://mlsanity.com/paper/2011.11660/) (2020)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Privacy in Deep Learning: A Survey](https://mlsanity.com/paper/2004.12254/) (2020)
- [Recent progress in semantic image segmentation](https://mlsanity.com/paper/1809.10198/) (2018)
- [Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings](https://mlsanity.com/paper/2010.06667/) (2020)
- [Model Explanations with Differential Privacy](https://mlsanity.com/paper/2006.09129/) (2020)
- [Advancements in Image Classification using Convolutional Neural Network](https://mlsanity.com/paper/1905.03288/) (2019)
- [Local Differential Privacy: a tutorial](https://mlsanity.com/paper/1907.11908/) (2019)
- [U-Noise: Learnable Noise Masks for Interpretable Image Segmentation](https://mlsanity.com/paper/2101.05791/) (2021)
- [Benchmarking Differentially Private Residual Networks for Medical Imagery](https://mlsanity.com/paper/2005.13099/) (2020)
- [FedPandemic: A Cross-Device Federated Learning Approach Towards Elementary Prognosis of Diseases During a Pandemic](https://mlsanity.com/paper/2104.01864/) (2021)

## Built on by (most cited first, 8 of 8)

- [Privacy Meets Explainability: A Comprehensive Impact Benchmark](https://mlsanity.com/paper/2211.04110/) (2022)
- [A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures](https://mlsanity.com/paper/2404.00673/) (2024)
- [SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning](https://mlsanity.com/paper/2312.16191/) (2023)
- [Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability](https://mlsanity.com/paper/2404.06144/) (2024)
- [Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models](https://mlsanity.com/paper/2308.08774/) (2023)
- [Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense](https://mlsanity.com/paper/2602.03611/) (2026)
- [Tensions Between the Proxies of Human Values in AI](https://mlsanity.com/paper/2212.07508/) (2022)
- [Which PPML Would a User Choose? A Structured Decision Support Framework for Developers to Rank PPML Techniques Based on User Acceptance Criteria](https://mlsanity.com/paper/2411.06995/) (2024)

## Abstract (arXiv)

Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is surging in importance and there is a large body of work focusing on providing better privacy-utility trade-off. However, little attention is given to the interpretability of these models, and how the application of DP affects the quality of interpretations. We propose an extensive study into the effects of DP training on DNNs, especially on medical imaging applications, on the APTOS dataset.