# Robust or Private? Adversarial Training Makes Models More Vulnerable to Privacy Attacks

arXiv: https://arxiv.org/abs/1906.06449 · HTML: https://mlsanity.com/paper/1906.06449/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [Reconstructing Training Data from Trained Neural Networks](https://mlsanity.com/paper/2206.07758/) (2022)
- [Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations](https://mlsanity.com/paper/2201.12961/) (2022)
- [Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning](https://mlsanity.com/paper/2105.07985/) (2021)
- [Closing the Train-Test Gap in World Models for Gradient-Based Planning](https://mlsanity.com/paper/2512.09929/) (2025)
- [Privacy Leakage of Adversarial Training Models in Federated Learning Systems](https://mlsanity.com/paper/2202.10546/) (2022)
- [Differentially Private Optimizers Can Learn Adversarially Robust Models](https://mlsanity.com/paper/2211.08942/) (2022)
- [SoK: Unintended Interactions among Machine Learning Defenses and Risks](https://mlsanity.com/paper/2312.04542/) (2023)
- [Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond](https://mlsanity.com/paper/2503.07501/) (2025)
- [Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks](https://mlsanity.com/paper/2310.08681/) (2023)
- [Reducing information dependency does not cause training data privacy. Adversarially non-robust features do](https://mlsanity.com/paper/2607.12354/) (2026)
- [Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff](https://mlsanity.com/paper/2610.07677/) (2026)

## Abstract (arXiv)

Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy attacks. In this work we demonstrate how model inversion attacks, extracting training data directly from the model, previously thought to be intractable become feasible when attacking a robustly trained model. The input space for a traditionally trained model is dominated by adversarial examples - data points that strongly activate a certain class but lack semantic meaning - this makes it difficult to successfully conduct model inversion attacks. We demonstrate this effect using the CIFAR-10 dataset under three different model inversion attacks, a vanilla gradient descent method, gradient based method at different scales, and a generative adversarial network base attacks.