# A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications

arXiv: https://arxiv.org/abs/2307.02984 · HTML: https://mlsanity.com/paper/2307.02984/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Refacing: reconstructing anonymized facial features using GANs](https://mlsanity.com/paper/1810.06455/) (2018)
- [k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment](https://mlsanity.com/paper/2303.10824/) (2023)

## Built on by (most cited first, 5 of 5)

- [Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.17004/) (2023)
- [Privacy-preserving datasets by capturing feature distributions with Conditional VAEs](https://mlsanity.com/paper/2408.00639/) (2024)
- [Generative Medical Image Anonymization Based on Latent Code Projection and Optimization](https://mlsanity.com/paper/2501.09114/) (2025)
- [Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Data](https://mlsanity.com/paper/2505.14206/) (2025)
- [Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation](https://mlsanity.com/paper/2510.01793/) (2025)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have demonstrated their ability to generate synthetic samples that match a target distribution. However, from a privacy perspective, using GANs as a proxy for data sharing is not a safe solution, as they tend to embed near-duplicates of real samples in the latent space. Recent works, inspired by k-anonymity principles, address this issue through sample aggregation in the latent space, with the drawback of reducing the dataset by a factor of k. Our work aims to mitigate this problem by proposing a latent space navigation strategy able to generate diverse synthetic samples that may support effective training of deep models, while addressing privacy concerns in a principled way. Our approach leverages an auxiliary identity classifier as a guide to non-linearly walk between points in the latent space, minimizing the risk of collision with near-duplicates of real samples. We empirically demonstrate that, given any random pair of points in the latent space, our walking strategy is safer than linear interpolation. We then test our path-finding strategy combined to k-same methods and demonstrate, on two benchmarks for tuberculosis and diabetic retinopathy classification, that training a model using samples generated by our approach mitigate drops in performance, while keeping privacy preservation.