Learning Universal Adversarial Perturbations with Generative Models

By Jamie Hayes, George Danezis. 2017

170 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Adil Karjauv
2. Chenguo Lin
3. Jing Wu
4. In-So Kweon
5. Chaoning Zhang
6. Philipp Benz

In Computer Vision and Pattern Recognition

1. Adil Karjauv
2. Chenguo Lin
3. Jing Wu
4. In-So Kweon
5. Chaoning Zhang
6. Philipp Benz
7. Luc Van Gool
8. Dacheng Tao

Citations in the corpus

• A Survey On Universal Adversarial Attack (2021, result): “Concurrent to this, the authors of [Hayes and Danezis, 2018] also explored the idea of generating adversarial perturbations with a generator network.”