DeepFake Detection for Human Face Images and Videos: A Survey

Malik, Asad; Kuribayashi, Minoru; Abdullahi, Sani M.; Khan, Ahmad Neyaz

doi:10.1109/access.2022.3151186

Cited by 89 publications

(22 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leaky ReLU is also used at this layer as an activation function. Since it is the first layer extracting image features, it is going to be a high-level feature of input images, and thus, the filter size is kept to be small, i.e., (3,3) instead of a larger filter such as (5,5) or (7,7). With this, we now have the initial feature maps extracted from the input images, but the distributions of input batches can vary a lot for different batches based on the types of images that are included in them.…”

Section: B Proposed Architecturementioning

confidence: 99%

“…An iterative process is followed in the generator-discriminator network, where the discriminator feedback is supplied to the generator network. Over time, the generator learns to create synthetic content, which looks extremely real and spoofs the discriminator [4] [5]. Thus, the generator-discriminator network in DF raises concerns about the authenticity of the published content on social platforms, as it is tough to differentiate between real and fake content.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Improved Dense CNN Architecture for Deepfake Image Detection

et al. 2023

View full text Add to dashboard Cite

Recent advancements in computer vision processing need potent tools to create realistic deepfakes. A generative adversarial network (GAN) can fake the captured media streams, such as images, audio, and video, and make them visually fit other environments. So, the dissemination of fake media streams creates havoc in social communities and can destroy the reputation of a person or a community. Moreover, it manipulates public sentiments and opinions toward the person or community. Recent studies have suggested using the convolutional neural network (CNN) as an effective tool to detect deepfakes in the network. But, most techniques cannot capture the inter-frame dissimilarities of the collected media streams. Motivated by this, this paper presents a novel and improved deep-CNN (D-CNN) architecture for deepfake detection with reasonable accuracy and high generalizability. Images from multiple sources are captured to train the model, improving overall generalizability capabilities. The images are re-scaled and fed to the D-CNN model. A binary-cross entropy and Adam optimizer are utilized to improve the learning rate of the D-CNN model. We have considered seven different datasets from the reconstruction challenge with 5000 deepfake images and 10000 real images. The proposed model yields an accuracy of 98.33% in AttGAN a , 99.33% in GDWCT b , 95.33% in StyleGAN, 94.67% in StyleGAN2, and 99.17% in StarGAN c real and deepfake images, that indicates its viability in experimental setups. a Facial Attribute Editing by Only Changing What You Want (AttGAN) b Group-wise deep whitening-and-coloring transformation (GDWCT) c A GAN capable of learning mappings among multiple domains (StarGAN)

show abstract

Section: B Proposed Architecturementioning

confidence: 99%

mentioning

confidence: 99%

An Improved Dense CNN Architecture for Deepfake Image Detection

et al. 2023

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

“…Numerous surveys and literature reviews have been published following the recent explosion in DeepFake research [38,45,49,55]. After reviewing the creation tools and detection approaches of DeepFakes, the authors of [45] focus on the challenges for robust DeepFake detection, such as the handling of adversarial attacks. Also, [49] reviews extensively the technical background of Deep-Fakes in terms of Generative Adversarial Networks (GANs), Neural Networks and Loss functions with a particular focus on Facial Reenactment techniques, such as [70].…”

Section: Related Workmentioning

confidence: 99%

The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild

Baxevanakis¹,

Kordopatis-Zilos²,

Galopoulos³

et al. 2022

Preprint

View full text Add to dashboard Cite

Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams. CCS CONCEPTS• Information systems → Multimedia information systems; Web services; Data analytics; • Security and privacy → Human and societal aspects of security and privacy.

show abstract

“…D EEPFAKE is a technique for creating synthetic content by naturally changing the human face of the original content using an autoencoder and generative adversarial network (GAN) [1,2,3]. In a broad sense, deepfake refers to deformed or created content that uses deep learning methods (audio deepfake [4], imaginary people generation [5], etc.)…”

Section: Introductionmentioning

confidence: 99%

Detection Enhancement for Various Deepfake Types Based on Residual Noise and Manipulation Traces

Kang

Lee

et al. 2022

IEEE Access

View full text Add to dashboard Cite

As deepfake techniques become more sophisticated, the demand for fake facial image detection continues to increase. Various deepfake detection techniques have been introduced but detecting all types of deepfake images with a single model remains challenging. We propose a technique for detecting various types of deepfake images using three common traces generated by deepfakes: residual noise, warping artifacts, and blur effects. We adopted a network designed for steganalysis to detect pixel-wise residual-noise traces. We also consider landmarks, which are the primary parts of the face where unnatural deformations often occur in deepfake images, to capture high-level features. Finally, because the effect of a deepfake is similar to that of blurring, we apply features from various image quality measurement tools that can capture traces of blurring. The results demonstrate that each detection strategy is efficient, and that the performance of the proposed network is stable and superior to that of existing detection networks on datasets of various deepfake types.INDEX TERMS deepfake forensics, image forensics, residual noise, warping artifact, image quality measurement

show abstract

DeepFake Detection for Human Face Images and Videos: A Survey

Cited by 89 publications

References 98 publications

An Improved Dense CNN Architecture for Deepfake Image Detection

An Improved Dense CNN Architecture for Deepfake Image Detection

The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild

Detection Enhancement for Various Deepfake Types Based on Residual Noise and Manipulation Traces

Contact Info

Product

Resources

About