# Deep generative models as an adversarial attack strategy for tabular machine learning

arXiv: https://arxiv.org/abs/2409.12642 · HTML: https://mlsanity.com/paper/2409.12642/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 19 Sep 2024.

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

- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [Constructing Unrestricted Adversarial Examples with Generative Models](https://mlsanity.com/paper/1805.07894/) (2018)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN](https://mlsanity.com/paper/1702.05983/) (2017)
- [IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection](https://mlsanity.com/paper/1809.02077/) (2018)
- [How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data](https://mlsanity.com/paper/2402.04823/) (2024)
- [OCT-GAN: Neural ODE-based Conditional Tabular GANs](https://mlsanity.com/paper/2105.14969/) (2021)
- [Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis](https://mlsanity.com/paper/2202.03636/) (2022)
- [AI-GAN: Attack-Inspired Generation of Adversarial Examples](https://mlsanity.com/paper/2002.02196/) (2020)
- [A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space](https://mlsanity.com/paper/2112.01156/) (2021)
- [AdvGAN++ : Harnessing latent layers for adversary generation](https://mlsanity.com/paper/1908.00706/) (2019)
- [AdvFoolGen: Creating Persistent Troubles for Deep Classifiers](https://mlsanity.com/paper/2007.10485/) (2020)
- [Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data](https://mlsanity.com/paper/2311.04503/) (2023)

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

- [Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Review](https://mlsanity.com/paper/2506.15506/) (2025)

## Abstract (arXiv)

Deep Generative Models (DGMs) have found application in computer vision for generating adversarial examples to test the robustness of machine learning (ML) systems. Extending these adversarial techniques to tabular ML presents unique challenges due to the distinct nature of tabular data and the necessity to preserve domain constraints in adversarial examples. In this paper, we adapt four popular tabular DGMs into adversarial DGMs (AdvDGMs) and evaluate their effectiveness in generating realistic adversarial examples that conform to domain constraints.