# Learning Universal Adversarial Perturbations with Generative Models

arXiv: https://arxiv.org/abs/1708.05207 · HTML: https://mlsanity.com/paper/1708.05207/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2017.

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

- [Mitigating Black-Box Adversarial Attacks via Output Noise Perturbation](https://mlsanity.com/paper/2109.15160/) (2021)
- [Surround-View Cameras based Holistic Visual Perception for Automated Driving](https://mlsanity.com/paper/2206.05542/) (2022)
- [Adversarial Robustness: What fools you makes you stronger](https://mlsanity.com/paper/2102.05475/) (2021)
- [Adversarial Vulnerability Transcends Computational Paradigms: Feature Engineering Provides No Defense Against Neural Adversarial Transfer](https://mlsanity.com/paper/2601.21323/) (2026)

## Abstract (arXiv)

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and classifier, there exists so called universal adversarial perturbations, a single perturbation that causes a misclassification when applied to any input. In this work, we introduce universal adversarial networks, a generative network that is capable of fooling a target classifier when it's generated output is added to a clean sample from a dataset. We show that this technique improves on known universal adversarial attacks.