Watching the BiG artifacts: Exposing DeepFake videos via Bi-granularity artifacts

Chen, Han; Li, Yuezun; Lin, Dongdong; Li, Bin; Wu, Junqiang

doi:10.1016/j.patcog.2022.109179

Cited by 22 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, attention mechanism, augmentation of partial data, and clustering of individual samples are employed to improve the model's robustness. Chen et al [65] exploited a different trace which is bi-granularity artifacts, intrinsic-granularity artifacts that are caused by up-convolution or up-sampling operations, and extrinsic granularity artifacts that are the result of the post-processing step that blends the synthesized face to the original video. Deepfake detection is tackled as a multi-task learning problem where ResNet-18 is used as the backbone feature extractor.…”

Section: Detection Based On Convolutional Tracesmentioning

confidence: 99%

Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions

Naitali,

Ridouani,

Salahdine

et al. 2023

Computers

View full text Add to dashboard Cite

Recent years have seen a substantial increase in interest in deepfakes, a fast-developing field at the nexus of artificial intelligence and multimedia. These artificial media creations, made possible by deep learning algorithms, allow for the manipulation and creation of digital content that is extremely realistic and challenging to identify from authentic content. Deepfakes can be used for entertainment, education, and research; however, they pose a range of significant problems across various domains, such as misinformation, political manipulation, propaganda, reputational damage, and fraud. This survey paper provides a general understanding of deepfakes and their creation; it also presents an overview of state-of-the-art detection techniques, existing datasets curated for deepfake research, as well as associated challenges and future research trends. By synthesizing existing knowledge and research, this survey aims to facilitate further advancements in deepfake detection and mitigation strategies, ultimately fostering a safer and more trustworthy digital environment.

show abstract

Section: Detection Based On Convolutional Tracesmentioning

confidence: 99%

Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions

Naitali,

Ridouani,

Salahdine

et al. 2023

Computers

View full text Add to dashboard Cite

show abstract

“…With a very tiny amount of calculation, this module may bring the previous feature's attention information to the present feature and increase the positioning accuracy of the fusion feature based on the channel attention level. The forgery localization 99.95 68.22 72.03 FRLM [28] 99.50 70.58 68.17 F3Net [20] 98.10 71.21 86.10 DMGTN [29] 99.80 72.30 -Face-X-ray [30] 87.40 74.20 85.60 MLDG [31] 98.99 74.56 88.14 GFF [32] 98.36 75.31 85.51 SFDG [33] 99.53 75.83 88.00 SOLA [34] 99.25 76.02 -MultiAtt [35] 99.27 76.65 87.58 BiG-Arts [36] 99.39 77.04 89.92 LTW [37] 99.17 77.14 88.56 FAAFF [38] 99. loss is defined as follows:…”

Section: Forgery Localization Module With Multi-level Feature Fusionmentioning

confidence: 99%

Learnable Local Similarity for Face Forgery Detection and Localization

Leng,

Fei,

Dai

2023

IJACSA

View full text Add to dashboard Cite

The emergence of many face forgery technologies has led to the widespread of forgery faces on the Internet, causing a series of serious social impacts, thus face forgery detection technology has attracted increasing attention. While many face forgery detection algorithms have demonstrated impressive performance against known manipulation methods, their efficacy tends to diminish severely when applied to unknown forgeries. Previous research commonly viewed face forgery detection as a binary classification problem, disregarding the crucial distinction between real and forged faces, thereby limiting the generalizability of detection algorithms. To overcome this issue, this paper proposes a novel face forgery detection method that utilizes a trainable metric to learn local similarity between local features of facial images, achieving a more generalized detection result. What's more, it incorporate cross-level features to accurately locate forgery regions. After conducting extensive experiments on FaceForensics++, Celeb-DF-v2, and DFD, which demonstrate that the effectiveness of the proposed method is comparable to state-of-the-art detection algorithms.

show abstract

DIFLD: domain invariant feature learning to detect low-quality compressed face forgery images

Zou,

Luo,

Zhang

2023

Complex Intell. Syst.

View full text Add to dashboard Cite

With the rapid development of deep learning, face forgery detection methods have also achieved remarkable progress. However, most methods suffer significant performance degradation on low-quality compressed face images. It is due to: (a) The image artifacts will be blurred in the process of image compression, resulting in the model learning insufficient artifact traces; (b) Low-quality images will introduce a lot of noise information, and minimizing the training error causes the model to absorb all correlations in the training dataset recklessly, leading to the over-fitting problem. To solve the above problems, we consider learning domain invariant representations to inscribe the correct relevance, i.e., artifacts, to improve the robustness of low-quality images. Specifically, we propose a novel face forgery detector, called DIFLD. The model has the following components: (1) a high-frequency invariant feature learning module(hf-IFLM), which effectively retrieves the blurred artifacts in low-quality compressed images; and (2) a high-dimensional feature distribution learning module(hd-FDLM), that guides the network to learn more about the consistent features of distribution. With the above two modules, the whole framework can learn more discriminative correct artifact features in an end-to-end manner. Through extensive experiments, we show that our proposed method is more robust to image quality variations, especially in low-quality images. Our proposed method achieves a 3.67% improvement over the state-of-the-art methods on the challenging dataset NeuralTextures.

show abstract

Watching the BiG artifacts: Exposing DeepFake videos via Bi-granularity artifacts

Cited by 22 publications

References 8 publications

Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions

Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions

Learnable Local Similarity for Face Forgery Detection and Localization

DIFLD: domain invariant feature learning to detect low-quality compressed face forgery images

Contact Info

Product

Resources

About