Leveraging edges and optical flow on faces for deepfake detection

Chintha, Akash; Rao, Aishwarya Govinda; Sohrawardi, Saniat Javid; Bhatt, Kartavya; Wright, Matthew; Ptucha, Raymond

doi:10.1109/ijcb48548.2020.9304936

Cited by 17 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their network, XceptionNet, performs very well (99% authenticity verification correctness on raw images, 81% on compressed) [29]. This has inspired numerous other high-performing models [30], where some introduce multi-stream fusion [31], multi-task learning [32] and optical flow [33].…”

Section: Deep-learning Tampering Detectionmentioning

confidence: 98%

Efficiently Mitigating Face-Swap-Attacks: Compressed-PRNU Verification with Sub-Zones

2022

View full text Add to dashboard Cite

Face-swap-attacks (FSAs) are a new threat to face recognition systems. FSAs are essentially imperceptible replay-attacks using an injection device and generative networks. By placing the device between the camera and computer device, attackers can present any face as desired. This is particularly potent as it also maintains liveliness features, as it is a sophisticated alternation of a real person, and as it can go undetected by traditional anti-spoofing methods. To address FSAs, this research proposes a noise-verification framework. Even the best generative networks today leave alteration traces in the photo-response noise profile; these are detected by doing a comparison of challenge images against the camera enrollment. This research also introduces compression and sub-zone analysis for efficiency. Benchmarking with open-source tampering-detection algorithms shows the proposed compressed-PRNU verification robustly verifies facial-image authenticity while being significantly faster. This demonstrates a novel efficiency for mitigating face-swap-attacks, including denial-of-service attacks.

show abstract

Section: Deep-learning Tampering Detectionmentioning

confidence: 98%

Efficiently Mitigating Face-Swap-Attacks: Compressed-PRNU Verification with Sub-Zones

2022

View full text Add to dashboard Cite

show abstract

“…Images compression algorithms and compression rates are not the same. Thus, Chintha et al [40] fed images frames and dense optical flow maps into the network together, which was very effective against adversarial attacks. In a similar way, Cheng et al [41] input the RGB image and the spectral map transformed by DCT into two branch networks, and then fuse RGB feature maps and frequency feature maps.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, Chintha et al. [40] fed images frames and dense optical flow maps into the network together, which was very effective against adversarial attacks. In a similar way, Cheng et al.…”

Section: Related Workmentioning

confidence: 99%

MCDC‐Net: Multi‐scale forgery image detection network based on central difference convolution

He,

Jiang,

Jin

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) emerged thanks to the development of deep neural networks. Forgery images generated by various variants of GANs are widely spread on the Internet, which may be damage personal credibility and cause huge property losses. Thus, numerous methods are proposed to detect forgery images, but most of them are designed to detect forgery faces. Therefore, a method to detect forgery images of various scenes is proposed. In this work, central difference convolution and vanilla convolution (CDC‐Mix) are mixed after considering the depth and width features of neural networks and analyzing the influence of attention on network performance. Based on CDC‐Mix, a separable convolution (SeparableCDC‐Mix) is proposed. The proposed method consists of three parts: (1) CDC‐Mix and SeparableCDC‐Mix are used to extract the gradient information and texture features; (2) CDCM is used to extract the multi‐scale information of the image; (3) multi‐scale fusion module (MS‐Fusion) is used to fuse the multi‐scale information from different locations of the network. A large number of experiments have been carried out on several datasets generated by GAN, and the experimental results show that the proposed method has a great improvement compared with the existing advanced methods.

show abstract

“…In addition to the technological aspects associated with the production and detection of deep fakes, the ethical, social, and legal implications have also been meticulously explored. There have already been some reviews written in particular sectors, such as the creation and detection of deepfakes [21], law [22], forensics [23], and social impact [24], to name just a few of these areas. Nevertheless, none of them considers the entire breadth of research fields in deepfakes, which we believe might be highly valuable for academics who intend to work on this research issue [25].…”

Section: Review Articlementioning

confidence: 99%

Deepfakes in Cyber Warfare: Threats, Detection, Techniques and Countermeasures

Cinar

2023

AJRCoS

View full text Add to dashboard Cite

Technology known as deepfake (DT) has reached an entirely new level of complexity. Cybercriminals now have the ability to modify sounds, images, and videos in order to mislead individuals and businesses and spread false information. This constitutes a rising threat to international organizations as well as individuals, and it is imperative that something be done about it. This article presents an overview of deepfakes, discussing their usefulness to society as well as the operation of DT. This article focuses on the dangers that can be posed by deep fakes to the economic, political, and legal institutions of countries all over the world. In addition to this, the study will investigate various solutions to the problem of deepfakes, and it will finish by discussing potential directions for further research.

show abstract

Leveraging edges and optical flow on faces for deepfake detection

Cited by 17 publications

References 38 publications

Efficiently Mitigating Face-Swap-Attacks: Compressed-PRNU Verification with Sub-Zones

Efficiently Mitigating Face-Swap-Attacks: Compressed-PRNU Verification with Sub-Zones

MCDC‐Net: Multi‐scale forgery image detection network based on central difference convolution

Deepfakes in Cyber Warfare: Threats, Detection, Techniques and Countermeasures

Contact Info

Product

Resources

About