# Adversarial Attacks Against Deep Generative Models on Data: A Survey

arXiv: https://arxiv.org/abs/2112.00247 · HTML: https://mlsanity.com/paper/2112.00247/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2021.

## Built on by (most cited first, 24 of 24)

- [Raising the Cost of Malicious AI-Powered Image Editing](https://mlsanity.com/paper/2302.06588/) (2023)
- [A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks](https://mlsanity.com/paper/2406.06186/) (2024)
- [Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond](https://mlsanity.com/paper/2306.00419/) (2023)
- [Generative Adversarial Networks Unlearning](https://mlsanity.com/paper/2308.09881/) (2023)
- [U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI](https://mlsanity.com/paper/2406.15386/) (2024)
- [My Art My Choice: Adversarial Protection Against Unruly AI](https://mlsanity.com/paper/2309.03198/) (2023)
- [A Systematic Review of Federated Generative Models](https://mlsanity.com/paper/2405.16682/) (2024)
- [Adversarial robustness of VAEs through the lens of local geometry](https://mlsanity.com/paper/2208.03923/) (2022)
- [Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process](https://mlsanity.com/paper/2303.01234/) (2023)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Generative Artificial Intelligence in Healthcare: Ethical Considerations and Assessment Checklist](https://mlsanity.com/paper/2311.02107/) (2023)
- [PFGuard: A Generative Framework with Privacy and Fairness Safeguards](https://mlsanity.com/paper/2410.02246/) (2024)
- [Preserving Privacy in GANs Against Membership Inference Attack](https://mlsanity.com/paper/2311.03172/) (2023)
- [Sharing is CAIRing: Characterizing Principles and Assessing Properties of Universal Privacy Evaluation for Synthetic Tabular Data](https://mlsanity.com/paper/2312.12216/) (2023)
- [HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models](https://mlsanity.com/paper/2512.00094/) (2025)
- [A supervised generative optimization approach for tabular data](https://mlsanity.com/paper/2309.05079/) (2023)
- [Six Levels of Privacy: A Framework for Financial Synthetic Data](https://mlsanity.com/paper/2403.14724/) (2024)
- [A Deep Generative Framework for Joint Households and Individuals Population Synthesis](https://mlsanity.com/paper/2407.01643/) (2024)
- [Securing AI Systems: A Guide to Known Attacks and Impacts](https://mlsanity.com/paper/2506.23296/) (2025)
- [Securing generative artificial intelligence with parallel magnetic tunnel junction true randomness](https://mlsanity.com/paper/2510.01598/) (2025)
- [PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure](https://mlsanity.com/paper/2511.07997/) (2025)
- [F2AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns](https://mlsanity.com/paper/2310.14561/) (2023)
- [Explore the vulnerability of black-box models via diffusion models](https://mlsanity.com/paper/2506.07590/) (2025)
- [Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks](https://mlsanity.com/paper/2609.10608/) (2026)

## Abstract (arXiv)

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks and variational auto-encoders. Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. These models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/ VAEs, the discriminators/encoders of GANs/ VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field.