Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

1-2021

Abstract

In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation. However, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge. In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AIsynthesized fake faces. The studies on neuron coverage and interactions have successfully shown that they can be served as testing criteria for deep learning systems, especially under the settings of being exposed to adversarial attacks. Here, we conjecture that monitoring neuron behavior can also serve as an asset in detecting fake faces since layer-bylayer neuron activation patterns may capture more subtle features that are important for the fake detector. Experimental results on detecting four types of fake faces synthesized with the state-of-the-art GANs and evading four perturbation attacks show the effectiveness and robustness of our approach.

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of the 29th International Joint Conference on Artificial Intelligence IJCAI 2020, Virtual Conference, January 7-15

First Page

3444

Last Page

3451

Identifier

10.5555/3491440.3491916

Publisher

ACM

City or Country

Virtual Conference

Comments

Main track

Share

COinS