Celeb-DF: A New Dataset for DeepFake Forensics

By Yuezun Li, Xin Yang, Honggang Qi, Siwei Lyu. 2019

211 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection (2022, methodology): “four methods in FF++ [41], and evaluate it on the benchmark datasets including CelebDF [28], DFDC [12], and DF1.”
On the Detection of Digital Face Manipulation (2019, unknown): “Methods Training data UADFV [58] Celeb-DF [31]”
Face X-Ray for More General Face Forgery Detection (2019, methodology): “DFD, DFDC and Celeb-DF, are shown in Table 2.”
Media Forensics and DeepFakes: An Overview (2020, methodology): “Many more, and much larger datasets include video manipulated with AIbased tools [215], [191], [178], [216], [217], [218], [219], [220] (Table III).”
The Creation and Detection of Deepfakes (2020, background): “Concretely, the three most recent benchmark datasets (DFD by Google [120], DFDC by Facebook [40], and Celeb-DF by [101]) were released within one month of each other at the end of 2019.”
A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials (2022, background): “To address this issue, many deepfake detection datasets (e.g.,[40, 44, 46, 21, 64, 19, 31]) and techniques (e.g., [87, 4, 80, 57, 56, 5]) are proposed.”
Creating, Using, Misusing, and Detecting Deep Fakes (2022, background): “Because this blending introduces a slight artifact along the facial boundary, a neural network can be trained to detect artifacts at the boundary of a stitched face (L. Li et al. 2019).”
The Deepfake Detection Challenge (DFDC) Preview Dataset (2019, methodology): “These include the Celeb-DF [4], UADFV [5], DeepFake-TIMIT [6], VTD dataset [7], FaceForensics [8] and its successor FaceForensics++ [9].”
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection (2020, methodology): “On another note, we observe high similarity between training and test videos, in terms of their distribution, in certain works [26, 33].”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, methodology): “These results have been extracted from [17] and were not included in the original publications.”
Emotions Don't Lie: An Audio-Visual Deepfake Detection Method using Affective Cues (2020, unknown): “UADFV [61] Nov 2018 49 49 98 YouTube FakeApp [2] ✓ × DF-TIMIT [33] Dec 2018 0 620 620∗ VidTIMIT [52] FS_GAN [5] ✓ ✓ Face Forensics++ [49] Jan 2019 1,000 4,000 5,000 YouTube FS [1], DF ✓ × DFD [6] Sep 2019 361 3,070 3,431 YouTube DF ✓ × CelebDF [37] Nov 2019 408 795 1,203 YouTube DF ✓ × DFDC [23] Oct”
UCF: Uncovering Common Features for Generalizable Deepfake Detection (2023, methodology): “Specifically, we train all models on FF++ and evaluate their performance on FF++ [33], DFD [10], DFDC [11], and CelebDF [23].”