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

Li, Yuezun; Yang, Xin; Sun, Peipei; Qi, Honggang; Lyu, Siwei

doi:10.48550/arxiv.1909.12962

Cited by 29 publications

(62 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Li et al have presented in [17] a new database named Celeb-DF. This database aims to provide fake videos of better visual qualities, similar to the popular videos that are available online 15 , as previous databases exhibit low visual quality with many visible artifacts.…”

Section: Face Swap a Manipulation Techniques And Public Databasesmentioning

confidence: 99%

“…VI we describe the key elements of each type of facial manipulation including public databases for research, detection methods, For Face Synthesis, real images are extracted from http://www.whichfaceisreal.com/ and fake images from https://thispersondoesnotexist.com. For Face Swap, face images are extracted from Celeb-DF database [17]. For Facial Attributes, real images are extracted from http://www.whichfaceisreal.com/ and fake images are generated using FaceApp.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

Tolosana¹,

Vera-Rodríguez²,

Fiérrez³

et al. 2020

Preprint

View full text Add to dashboard Cite

The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake contents with its corresponding implications towards society in this era of fake news.This survey provides a thorough review of techniques for manipulating face images including DeepFake methods, and methods to detect such manipulations. In particular, four types of facial manipulation are reviewed: i) entire face synthesis, ii) face identity swap (DeepFakes), iii) facial attributes manipulation, and iv) facial expression manipulation. For each manipulation type, we provide details regarding manipulation techniques, existing public databases, and key benchmarks for technology evaluation of fake detection methods, including a summary of results from those evaluations. Among the different databases available and discussed in the survey, FaceForensics++ is for example one of the most widely used for detecting both face identity swap and facial expression manipulations, with results in the literature in the range of 90-100% of manipulation detection accuracy.In addition to the survey information, we also discuss trends and provide an outlook of the ongoing work in this field, e.g., the recently announced DeepFake Detection Challenge (DFDC).

show abstract

Section: Face Swap a Manipulation Techniques And Public Databasesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

Tolosana¹,

Vera-Rodríguez²,

Fiérrez³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Capsule Forensics uses a dynamic routing algorithm to generate an activation map where the face has been manipulated. As we can see in [4], these approaches dont generalize well on new and more challenging datasets. From [3], we can see many approaches [9]- [14] perform well when the resolution of the video is high.…”

Section: Deepfakes Video Classificationmentioning

confidence: 99%

“…Contributions In this paper, our main contributions are as follows: 1) Improve the binary classification of Deepfakes on new second-generation Celeb-DF [4] dataset and the FF++ dataset [3], using a metric learning approach. 2) Experimentally demonstrating the performance of various contemporary methods and their variations to classify videos in high compression factors on the FF++ dataset.…”

Section: Introductionmentioning

confidence: 99%

Detecting Deepfakes with Metric Learning

Kumar

Bhavsar

Verma³

2020

2020 8th International Workshop on Biometrics and Forensics (IWBF)

View full text Add to dashboard Cite

With the arrival of several face-swapping applications such as FaceApp, SnapChat, MixBooth, FaceBlender and many more, the authenticity of digital media content is hanging on a very loose thread. On social media platforms, videos are widely circulated often at a high compression factor. In this work, we analyze several deep learning approaches in the context of deepfakes classification in high compression scenarios and demonstrate that a proposed approach based on metric learning can be very effective in performing such a classification. Using less number of frames per video to assess its realism, the metric learning approach using a triplet network architecture proves to be fruitful. It learns to enhance the feature space distance between the cluster of real and fake videos embedding vectors. We validated our approaches on two datasets to analyze the behavior in different environments. We achieved a state-of-theart AUC score of 99.2% on the Celeb-DF dataset and accuracy of 90.71% on a highly compressed Neural Texture dataset. Our approach is especially helpful on social media platforms where data compression is inevitable.

show abstract

“…In 2019, Facebook launched a deepfake detection challenge with prize money of one million U.S. dollars to accelerate research in this field [6]. Recently, Li et al [34] released the CelebDF dataset, which contains 5,639 deepfake videos. Although, these benchmark datasets help in improving the performance and diversifying methods.…”

Section: Introductionmentioning

confidence: 99%

One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework

Tariq,

Lee,

Woo

2021

Preprint

View full text Add to dashboard Cite

Deep learning-based video manipulation methods have become widely accessible to the masses. With little to no effort, people can quickly learn how to generate deepfake (DF) videos. While deep learning-based detection methods have been proposed to identify specific types of DFs, their performance suffers for other types of deepfake methods, including real-world deepfakes, on which they are not sufficiently trained. In other words, most of the proposed deep learning-based detection methods lack transferability and generalizability. Beyond detecting a single type of DF from benchmark deepfake datasets, we focus on developing a generalized approach to detect multiple types of DFs, including deepfakes from unknown generation methods such as DeepFake-in-the-Wild (DFW) videos. To better cope with unknown and unseen deepfakes, we introduce a Convolutional LSTM-based Residual Network (CLRNet), which adopts a unique model training strategy and explores spatial as well as the temporal information in a deepfakes. Through extensive experiments, we show that existing defense methods are not ready for real-world deployment. Whereas our defense method (CLRNet) achieves far better generalization when detecting various benchmark deepfake methods (97.57% on average). Furthermore, we evaluate our approach with a high-quality DeepFake-in-the-Wild dataset, collected from the Internet containing numerous videos and having more than 150,000 frames. Our CLRNet model demonstrated that it generalizes well against high-quality DFW videos by achieving 93.86% detection accuracy, outperforming existing state-of-the-art defense methods by a considerable margin.

show abstract

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

Cited by 29 publications

References 40 publications

DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

Detecting Deepfakes with Metric Learning

One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework

Contact Info

Product

Resources

About