Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics

Abstract

AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for large-scale datasets. However, current DeepFake datasets suffer from low visual quality and do not resemble DeepFake videos circulated on the Internet. We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• MesoNet: a Compact Facial Video Forgery Detection Network
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• Pose Guided Person Image Generation
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
• Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
• In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
• The Deepfake Detection Challenge (DFDC) Preview Dataset
• Use of a Capsule Network to Detect Fake Images and Videos
• Learning Rich Features for Image Manipulation Detection
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network

Cited by in corpus (13)

• Media Forensics and DeepFakes: an overview
• Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds
• One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• The DeepFake Detection Challenge (DFDC) Dataset
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• DeepFake Detection Based on the Discrepancy Between the Face and its Context
• Generalizing Face Forgery Detection with High-frequency Features
• 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
• Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses
• Trusted Media Challenge Dataset and User Study
• Exploring Adversarial Fake Images on Face Manifold