# Defending Against Adversarial Attacks by Leveraging an Entire GAN

arXiv: https://arxiv.org/abs/1805.10652 · HTML: https://mlsanity.com/paper/1805.10652/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2018.

## Built on by (most cited first, 4 of 4)

- [Generative AI for Physical Layer Communications: A Survey](https://mlsanity.com/paper/2312.05594/) (2023)
- [Stateful Detection of Model Extraction Attacks](https://mlsanity.com/paper/2107.05166/) (2021)
- [Machine Learning in NextG Networks via Generative Adversarial Networks](https://mlsanity.com/paper/2203.04453/) (2022)
- [Adversarial Examples are Misaligned in Diffusion Model Manifolds](https://mlsanity.com/paper/2401.06637/) (2024)

## Abstract (arXiv)

Recent work has shown that state-of-the-art models are highly vulnerable to adversarial perturbations of the input. We propose cowboy, an approach to detecting and defending against adversarial attacks by using both the discriminator and generator of a GAN trained on the same dataset. We show that the discriminator consistently scores the adversarial samples lower than the real samples across multiple attacks and datasets. We provide empirical evidence that adversarial samples lie outside of the data manifold learned by the GAN. Based on this, we propose a cleaning method which uses both the discriminator and generator of the GAN to project the samples back onto the data manifold. This cleaning procedure is independent of the classifier and type of attack and thus can be deployed in existing systems.