Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features

Sun, Zekun; Han, Yahong; Hua, Zeyu; Ruan, Na; Jia, Weijia

doi:10.1109/cvpr46437.2021.00361

Cited by 105 publications

(37 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HQ LQ ACC AUC ACC AUC Xception [26] 95.73 96.30 86.86 89.30 LRNet [28] -97.3 -95.7 Multi-attention [37] 97.60 99.29 88.69 90.40 LipForensics [14] 98.80 99.70 94.20 98.10 FDFL [17] 96.69 99.30 89.00 92.40 SPSL [21] 91 2 show that our method also has superior performance on Celeb-DF, achieving 91.76% ACC and 98.70% on video-level.…”

Section: Methodsmentioning

confidence: 99%

Identity-Referenced Deepfake Detection with Contrastive Learning

Shen

Zhao

Quan

2022

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

With current advancements in deep learning technology, it is becoming easier to create high-quality face forgery videos, causing concerns about the misuse of deepfake technology. In recent years, research on deepfake detection has become a popular topic. Many detection methods have been proposed, most of which focus on exploiting image artifacts or frequency domain features for detection. In this work, we propose using real images of the same identity as a reference to improve detection performance. Specifically, a real image of the same identity is used as a reference image and input into the model together with the image to be tested to learn the distinguishable identity representation, which is achieved by contrastive learning. Our method achieves superior performance on both Face-Forensics++ and Celeb-DF with relatively little training data, and also achieves very competitive results on cross-manipulation and cross-dataset evaluations, demonstrating the effectiveness of our solution. CCS CONCEPTS• Security and privacy → Social aspects of security and privacy; • Computing methodologies → Artificial intelligence; Image processing.

show abstract

Section: Methodsmentioning

confidence: 99%

Identity-Referenced Deepfake Detection with Contrastive Learning

Shen

Zhao

Quan

2022

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

show abstract

“…Li et al [48] focused on blending regions to recognize forged faces without relying on knowledge of specific face manipulation techniques. Sun et al [81] developed a temporal method for geometrically modeling discriminative features to improve robustness for highly compressed or noise corrupted videos.…”

Section: Robust Deepfake Detectionmentioning

confidence: 99%

Robust Deepfake On Unrestricted Media: Generation And Detection

Le¹,

Nguyen²,

Yamagishi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep learning have led to substantial improvements in deepfake generation, resulting in fake media with a more realistic appearance. Although deepfake media have potential application in a wide range of areas and are drawing much attention from both the academic and industrial communities, it also leads to serious social and criminal concerns. This chapter explores the evolution of and challenges in deepfake generation and detection. It also discusses possible ways to improve the robustness of deepfake detection for a wide variety of media (e.g., in-the-wild images and videos). Finally, it suggests a focus for future fake media research.

show abstract

“…Zhao et al (Zhao et al, 2021) proposed a model that exploits multiple spatial attention heads to learn various local parts of a face and the textural enhancement block to learn subtle facial artifacts. To reduce the model size and improve the efficiency, Sun et al (Sun et al, 2021) proposed a robust method based on the change of landmark positions in a video. These landmarks are calibrated by the neighbor frames.…”

Section: Review Of Related Workmentioning

confidence: 99%

DefakeHop++: An Enhanced Lightweight Deepfake Detector

Chen¹,

Hu²,

You³

et al. 2022

Preprint

View full text Add to dashboard Cite

On the basis of DefakeHop, an enhanced lightweight Deepfake detector called DefakeHop++ is proposed in this work. The improvements lie in two areas. First, DefakeHop examines three facial regions (i.e., two eyes and mouth) while De-fakeHop++ includes eight more landmarks for broader coverage. Second, for discriminant features selection, Defake-Hop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT). In DefakeHop++, rich spatial and spectral features are first derived from facial regions and landmarks automatically. Then, DFT is used to select a subset of discriminant features for classifier training. As compared with MobileNet v3 (a lightweight CNN model of 1.5M parameters targeting at mobile applications), DefakeHop++ has a model of 238K parameters, which is 16% of MobileNet v3. Furthermore, DefakeHop++ outperforms MobileNet v3 in Deepfake image detection performance in a weakly-supervised setting.

show abstract

Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features

Cited by 105 publications

References 22 publications

Identity-Referenced Deepfake Detection with Contrastive Learning

Identity-Referenced Deepfake Detection with Contrastive Learning

Robust Deepfake On Unrestricted Media: Generation And Detection

DefakeHop++: An Enhanced Lightweight Deepfake Detector

Contact Info

Product

Resources

About