# TraVaG: Differentially Private Trace Variant Generation Using GANs

arXiv: https://arxiv.org/abs/2303.16704 · HTML: https://mlsanity.com/paper/2303.16704/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 18 of 18)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS](https://mlsanity.com/paper/1912.06059/) (2019)
- [Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12](https://mlsanity.com/paper/1709.02753/) (2017)
- [Differentially Private Mixture of Generative Neural Networks](https://mlsanity.com/paper/1709.04514/) (2017)
- [Differentially Private Data Generative Models](https://mlsanity.com/paper/1812.02274/) (2018)
- [Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data](https://mlsanity.com/paper/1901.02477/) (2019)
- [Towards Formalizing the GDPR's Notion of Singling Out](https://mlsanity.com/paper/1904.06009/) (2019)
- [A Deep Learning Approach for Repairing Missing Activity Labels in Event Logs for Process Mining](https://mlsanity.com/paper/2202.10326/) (2022)
- [Towards Quantifying Privacy in Process Mining](https://mlsanity.com/paper/2012.12031/) (2020)
- [Mine Me but Don't Single Me Out: Differentially Private Event Logs for Process Mining](https://mlsanity.com/paper/2103.11739/) (2021)
- [Generating Privacy-Preserving Process Data with Deep Generative Models](https://mlsanity.com/paper/2203.07949/) (2022)
- [Libra: High-Utility Anonymization of Event Logs for Process Mining via Subsampling](https://mlsanity.com/paper/2206.13050/) (2022)
- [SaCoFa: Semantics-aware Control-flow Anonymization for Process Mining](https://mlsanity.com/paper/2109.08501/) (2021)
- [TraVaS: Differentially Private Trace Variant Selection for Process Mining](https://mlsanity.com/paper/2210.14951/) (2022)

## Built on by (most cited first, 3 of 3)

- [Control-flow Reconstruction Attacks on Business Process Models](https://mlsanity.com/paper/2409.10986/) (2024)
- [Releasing Differentially Private Event Logs Using Generative Models](https://mlsanity.com/paper/2504.06418/) (2025)
- [The Impact of Event Data Partitioning on Privacy-aware Process Discovery](https://mlsanity.com/paper/2507.06008/) (2025)

## Abstract (arXiv)

Process mining is rapidly growing in the industry. Consequently, privacy concerns regarding sensitive and private information included in event data, used by process mining algorithms, are becoming increasingly relevant. State-of-the-art research mainly focuses on providing privacy guarantees, e.g., differential privacy, for trace variants that are used by the main process mining techniques, e.g., process discovery. However, privacy preservation techniques for releasing trace variants still do not fulfill all the requirements of industry-scale usage. Moreover, providing privacy guarantees when there exists a high rate of infrequent trace variants is still a challenge. In this paper, we introduce TraVaG as a new approach for releasing differentially private trace variants based on Generative Adversarial Networks (GANs) that provides industry-scale benefits and enhances the level of privacy guarantees when there exists a high ratio of infrequent variants. Moreover, TraVaG overcomes shortcomings of conventional privacy preservation techniques such as bounding the length of variants and introducing fake variants. Experimental results on real-life event data show that our approach outperforms state-of-the-art techniques in terms of privacy guarantees, plain data utility preservation, and result utility preservation.