FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces

TL;DR

FakeSpotter is a neuron behavior-based method that effectively detects AI-synthesized fake faces, demonstrating robustness against various GAN types and adversarial attacks, addressing a critical security challenge.

Contribution

This paper introduces FakeSpotter, a novel neuron monitoring approach for detecting AI-generated fake faces, advancing robustness over existing methods.

Findings

Effective detection of four types of GAN-synthesized fake faces

Robust against four different perturbation attacks

Outperforms existing detection methods

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 AI-synthesized 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-by-layer 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.