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

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.

arXiv commentAccepted to IJCAI 2020; SOLE copyright holder is IJCAI (international Joint Conferences on Artificial Intelligence), all rights reserved. https://www.ijcai.org/Proceedings/2020/333

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• Identification of Deep Network Generated Images Using Disparities in Color Components
• Machine Learning Testing: Survey, Landscapes and Horizons
• Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
• Learning Rich Features for Image Manipulation Detection
• Interpreting the Latent Space of GANs for Semantic Face Editing
• Detecting GAN-generated Imagery using Color Cues
• Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
• Detecting GAN generated Fake Images using Co-occurrence Matrices
• Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
• Detecting and Simulating Artifacts in GAN Fake Images
• DeepMutation: Mutation Testing of Deep Learning Systems
• Detecting Photoshopped Faces by Scripting Photoshop
• Learning to Detect Fake Face Images in the Wild

Cited by in corpus (9)

• Fighting Deepfake by Exposing the Convolutional Traces on Images
• Fighting deepfakes by detecting GAN DCT anomalies
• On the Detection of Digital Face Manipulation
• Face X-ray for More General Face Forgery Detection
• Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attack
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
• Mining Generalized Features for Detecting AI-Manipulated Fake Faces
• [RE] CNN-generated images are surprisingly easy to spot...for now
• Generalizing Neural Networks by Reflecting Deviating Data in Production