Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics

• URL: http://arxiv.org/abs/2507.18015v1
• Date: Thu, 24 Jul 2025 01:12:28 GMT
• Title: Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
• Authors: Yuezun Li, Delong Zhu, Xinjie Cui, Siwei Lyu,
• Abstract summary: Celeb-DF++ is a new benchmark dedicated to the generalizable forensics challenge.<n>It covers three commonly encountered forgery scenarios: Face-swap (FS), Face-reenactment (FR), and Talking-face (TF)
• Score: 35.69057766374133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \textit{generalizable forensics}, \ie, detecting a wide range of unseen DeepFake types using a single model. Addressing this challenge requires datasets that are not only large-scale but also rich in forgery diversity. However, most existing datasets, despite their scale, include only a limited variety of forgery types, making them insufficient for developing generalizable detection methods. Therefore, we build upon our earlier Celeb-DF dataset and introduce {Celeb-DF++}, a new large-scale and challenging video DeepFake benchmark dedicated to the generalizable forensics challenge. Celeb-DF++ covers three commonly encountered forgery scenarios: Face-swap (FS), Face-reenactment (FR), and Talking-face (TF). Each scenario contains a substantial number of high-quality forged videos, generated using a total of 22 various recent DeepFake methods. These methods differ in terms of architectures, generation pipelines, and targeted facial regions, covering the most prevalent DeepFake cases witnessed in the wild. We also introduce evaluation protocols for measuring the generalizability of 24 recent detection methods, highlighting the limitations of existing detection methods and the difficulty of our new dataset.

Related papers

• Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection [43.2796409299818]
  Deepfakes are becoming a nuisance to law enforcement authorities and the general public.<n>Existing deepfake detectors are struggling to keep up with the pace of improvements in deepfake generation.<n>This paper proposes a new strategy that leverages coarse-to-fine spatial information, semantic information, and their interactions.
  arXiv  Detail & Related papers  (2025-05-08T01:49:53Z)
• DF40: Toward Next-Generation Deepfake Detection [62.073997142001424]
  existing works identify top-notch detection algorithms and models by adhering to the common practice: training detectors on one specific dataset and testing them on other prevalent deepfake datasets. But can these stand-out "winners" be truly applied to tackle the myriad of realistic and diverse deepfakes lurking in the real world? We construct a highly diverse deepfake detection dataset called DF40, which comprises 40 distinct deepfake techniques.
  arXiv  Detail & Related papers  (2024-06-19T12:35:02Z)
• Voice-Face Homogeneity Tells Deepfake [56.334968246631725]
  Existing detection approaches contribute to exploring the specific artifacts in deepfake videos. We propose to perform the deepfake detection from an unexplored voice-face matching view. Our model obtains significantly improved performance as compared to other state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-03-04T09:08:50Z)
• Model Attribution of Face-swap Deepfake Videos [39.771800841412414]
  We first introduce a new dataset with DeepFakes from Different Models (DFDM) based on several Autoencoder models. Specifically, five generation models with variations in encoder, decoder, intermediate layer, input resolution, and compression ratio have been used to generate a total of 6,450 Deepfake videos. We take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes.
  arXiv  Detail & Related papers  (2022-02-25T20:05:18Z)
• OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild [48.67582300190131]
  This paper presents a study on two new countermeasure tasks: multi-face forgery detection and segmentation in-the-wild. Localizing forged faces among multiple human faces in unrestricted natural scenes is far more challenging than the traditional deepfake recognition task. With its rich annotations, our OpenForensics dataset has great potentials for research in both deepfake prevention and general human face detection.
  arXiv  Detail & Related papers  (2021-07-30T08:15:41Z)
• One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework [19.762839181838388]
  We introduce a Convolutional LSTM-based Residual Network (CLRNet) to better cope with unknown and unseen deepfakes. Our CLRNet model demonstrated that it generalizes well against high-quality DFW videos by achieving 93.86% detection accuracy.
  arXiv  Detail & Related papers  (2021-05-01T08:02:59Z)
• Face Forensics in the Wild [121.23154918448618]
  We construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assessment network. In addition, we propose a novel algorithm to tackle the task of multi-person face forgery detection.
  arXiv  Detail & Related papers  (2021-03-30T05:06:19Z)
• The DeepFake Detection Challenge (DFDC) Dataset [8.451007921188019]
  Deepfakes are a technique that allows anyone to swap two identities in a single video. To counter this emerging threat, we have constructed an extremely large face swap video dataset. All recorded subjects agreed to participate in and have their likenesses modified during the construction of the face-swapped dataset.
  arXiv  Detail & Related papers  (2020-06-12T18:15:55Z)
• DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection [93.24684159708114]
  DeeperForensics-1.0 is the largest face forgery detection dataset by far, with 60,000 videos constituted by a total of 17.6 million frames. The quality of generated videos outperforms those in existing datasets, validated by user studies. The benchmark features a hidden test set, which contains manipulated videos achieving high deceptive scores in human evaluations.
  arXiv  Detail & Related papers  (2020-01-09T14:37:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.