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

By Run Wang, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Jian Wang, Yang Liu. 2019

60 citations recorded by the source corpus.

In recent years, we have witnessed the unprecedented success of generative adversarial networks (GANs) and its variants in image synthesis. These techniques are widely adopted in synthesizing fake faces which poses a serious challenge to existing face recognition (FR) systems and brings potential security threats to social networks and media as the fakes spread and fuel the misinformation. Unfortunately, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge. Currently, image forensic-based and learning-based approaches are the two major categories of strategies in detecting fake faces. In this work, we propose an alternative category of approaches based on monitoring neuron behavior. 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. Empirically, we have shown that the proposed FakeSpotter, based on neuron coverage behavior, in tandem with a simple linear classifier can greatly outperform deeply trained convolutional neural networks (CNNs) for spotting AI-synthesized fake faces. Extensive experiments carried out on three deep learning (DL) based FR systems, with two GAN variants for synthesizing fake faces, and on two public high-resolution face datasets have demonstrated the potential of the FakeSpotter serving as a simple, yet robust baseline for fake face detection in the wild.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

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

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

CNN-Generated Images Are Surprisingly Easy to Spot… for Now (2019, background): “Other work has proposed to detect GAN images using hand-crafted co-occurrence features [31], or by anomaly detection models built on pretrained face detectors [43].”
Analyzing and Improving the Image Quality of StyleGAN (2019, background): “At present, classifier-based methods can quite reliably detect generated images, regardless of their exact origin [24, 39, 35, 45, 36].”
The Creation and Detection of Deepfakes (2020, background): “Alternatively, to overcome noise and other distortions, the authors of [144] measured the neural activation (coverage) of a face recognition network to obtain a stronger signal from than just using the raw pixels.”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, background): “In [30], Wang et al. conjectured that monitoring neuron behavior could 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 facial manipulation detection system.”
Global Texture Enhancement for Fake Face Detection in the Wild (2020, background): “Recently, some researchers have investigated the problem of fake face detection [17, 26, 27, 23, 24, 32, 34, 30].”
Face X-Ray for More General Face Forgery Detection (2019, methodology): “FakeSpotter [47] uses layer-wise neuron behavior instead of only the last neuron output to train a binary classifier.”
GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection (2019, background): “In [13], Wang et al. conjectured that monitoring neuron behavior could 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 facial manipulation detection system.”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “The approach in [178] works well under the presence of compression operations but its performance degrades significantly for additive noise attacks.”