# Assessing Privacy Leakage in Synthetic 3-D PET Imaging using Transversal GAN

arXiv: https://arxiv.org/abs/2206.06448 · HTML: https://mlsanity.com/paper/2206.06448/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 13 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Temporal Generative Adversarial Nets with Singular Value Clipping](https://mlsanity.com/paper/1611.06624/) (2016)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation](https://mlsanity.com/paper/1810.04304/) (2018)
- [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks](https://mlsanity.com/paper/1807.10225/) (2018)
- [Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN](https://mlsanity.com/paper/1811.09245/) (2018)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Medical Image Synthesis with Context-Aware Generative Adversarial Networks](https://mlsanity.com/paper/1612.05362/) (2016)
- [Benchmarking Differentially Private Synthetic Data Generation Algorithms](https://mlsanity.com/paper/2112.09238/) (2021)
- [Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network](https://mlsanity.com/paper/1806.05473/) (2018)
- [Performing Co-Membership Attacks Against Deep Generative Models](https://mlsanity.com/paper/1805.09898/) (2018)
- [Squeeze-and-Excitation Normalization for Automated Delineation of Head and Neck Primary Tumors in Combined PET and CT Images](https://mlsanity.com/paper/2102.10446/) (2021)
- [A hierarchical approach to deep learning and its application to tomographic reconstruction](https://mlsanity.com/paper/1912.07743/) (2019)
- [3-D PET Image Generation with tumour masks using TGAN](https://mlsanity.com/paper/2111.01866/) (2021)

## Built on by (most cited first, 1 of 1)

- [Synthetic Cardiac MRI Image Generation using Deep Generative Models](https://mlsanity.com/paper/2603.24764/) (2026)

## Abstract (arXiv)

Training computer-vision related algorithms on medical images for disease diagnosis or image segmentation is difficult in large part due to privacy concerns. For this reason, generative image models are highly sought after to facilitate data sharing. However, 3-D generative models are understudied, and investigation of their privacy leakage is needed. We introduce our 3-D generative model, Transversal GAN (TrGAN), using head & neck PET images which are conditioned on tumour masks as a case study. We define quantitative measures of image fidelity, utility and privacy for our model. These metrics are evaluated in the course of training to identify ideal fidelity, utility and privacy trade-offs and establish the relationships between these parameters. We show that the discriminator of the TrGAN is vulnerable to attack, and that an attacker can identify which samples were used in training with almost perfect accuracy (AUC = 0.99). We also show that an attacker with access to only the generator cannot reliably classify whether a sample had been used for training (AUC = 0.51). This suggests that TrGAN generators, but not discriminators, may be used for sharing synthetic 3-D PET data with minimal privacy risk while maintaining good utility and fidelity.