FaceForensics++: Learning to Detect Manipulated Facial Images

Rössler, Andreas; Cozzolino, Davide; Verdoliva, Luisa; Rieß, Christian; Thies, Justus; Nießner, Matthias

doi:10.48550/arxiv.1901.08971

Cited by 27 publications

(99 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their approach showed limitations when detecting other types of manipulated images, such as DeepFakes. To help researchers better cope with different types of deepfakes, FaceForensics++ [30] was introduced, where FaceForensics++ provides benchmark datasets and an automatic metric that takes four realistic scenarios (i.e., random encoding and dimensions). With these benchmarks, they analyzed various methods of forgery detection pipelines.…”

Section: Image Forgery Detection With Neural Networkmentioning

confidence: 99%

“…For the face manipulation dataset, we downloaded datasets of various methods used for the experiment. FaceForen-sics++ [30] provides videos generated with FaceSwap [41], DeepFakes [42], Face2Face [43], and NeuralTextures [44]. We cropped the face region of the videos using MTCNN.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…FaceSwap. In our experiment, we used the dataset provided by FaceForensics++ [30], which implements a GitHub repository 1 . FaceSwap [41] changes the face of a target person to the source image face.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Various kinds of Deepfakes are available from different providers. For our experiment, we downloaded the dataset provided by FaceForensics++ [30], denoted as Deep-Fakes. FaceForenscis++ implements the faceswap GitHub [41] to generate the DeepFakes dataset.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…The difference with Neural Textures compared to traditional textures is that the stored highdimensional feature maps contain more information. The Face-Forensics++ [30] implements the idea and uses the original video data to learn a neural texture of the target person, including a rendering network. The difference is that the FaceForen-sics++ applies a patch-based GAN-loss from Pix2Pix [46].…”

Section: Dataset Descriptionmentioning

confidence: 99%

See 4 more Smart Citations

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

Bang¹,

Woo²

2021

Preprint

View full text Add to dashboard Cite

Due to the advancement of Generative Adversarial Networks (GAN), Autoencoders, and other AI technologies, it has been much easier to create fake images such as "Deepfakes." More recent research has introduced few-shot learning, which uses a small amount of training data to produce fake images and videos more effectively. Therefore, the ease of generating manipulated images and the difficulty of distinguishing those images can cause a serious threat to our society, such as propagating fake information. However, detecting realistic fake images generated by the latest AI technology is challenging due to the reasons mentioned above. In this work, we propose Dual Attention Fake Detection Fine-tuning Network (DA-FDFtNet) to detect the manipulated fake face images from the real face data. Our DA-FDFtNet integrates the pre-trained model with Fine-Tune Transformer, MBblockV3, and a channel attention module to improve the performance and robustness across different types of fake images. In particular, Fine-Tune Transformer consists of multiple numbers of an image-based self-attention module and a down-sampling layer. The channel attention module is also connected with the pre-trained model to capture the fake images feature space. We experiment with our DA-FDFtNet with the FaceForensics++ dataset and various GAN-generated datasets, and we show that our approach outperforms the previous baseline models.

show abstract

Section: Image Forgery Detection With Neural Networkmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

See 3 more Smart Citations

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

Bang¹,

Woo²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Chatbots as Villains: The Antisocial Uses of AI

Ciesla

2024

The Book of Chatbots

View full text Add to dashboard Cite

Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos

Nguyen

Fang

Yamagishi

et al. 2019

2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS)

321

126

View full text Add to dashboard Cite

Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query being manipulated. Another important topic is locating manipulated regions (i.e., performing segmentation), which are mostly created by three commonly used attacks: removal, copy-move, and splicing. We have designed a convolutional neural network that uses the multi-task learning approach to simultaneously detect manipulated images and videos and locate the manipulated regions for each query. Information gained by performing one task is shared with the other task and thereby enhance the performance of both tasks. A semi-supervised learning approach is used to improve the network's generability. The network includes an encoder and a Y-shaped decoder. Activation of the encoded features is used for the binary classification. The output of one branch of the decoder is used for segmenting the manipulated regions while that of the other branch is used for reconstructing the input, which helps improve overall performance. Experiments using the FaceForensics and Face-Forensics++ databases demonstrated the networks effectiveness against facial reenactment attacks and face swapping attacks as well as its ability to deal with the mismatch condition for previously seen attacks. Moreover, fine-tuning using just a small amount of data enables the network to deal with unseen attacks.

show abstract

FaceForensics++: Learning to Detect Manipulated Facial Images

Cited by 27 publications

References 0 publications

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

Chatbots as Villains: The Antisocial Uses of AI

Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos

Contact Info

Product

Resources

About