DFFMD: A Deepfake Face Mask Dataset for Infectious Disease Era With Deepfake Detection Algorithms

Alnaim, Norah; Almutairi, Zaynab; Alsuwat, Manal; Alalawi, Hana H.; Alshobaili, Aljowhra; Alenezi, Fayadh

doi:10.1109/access.2023.3246661

Cited by 22 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the approach achieves high detection accuracies of 97.39% and 95.65% for the Face2face and FaceSwap datasets, respectively, and attains 96.55% accuracy on the DFDC dataset, even when metrics are altered. NORAH M. ALNAIM, ZAYNAB M. ALMUTAIRI, et al, [7] Detecting contemporary Deepfakes presents an increasingly intricate and crucial challenge to address, impacting realms such as security, criminal activities, personal safety, large-scale politics, and societal dynamics.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Survey: Analysis and Detection of Deepfake in Multimedia Through Advanced Deep Learning Approaches

2024

IRJMETS

View full text Add to dashboard Cite

The evolution of multimedia manipulation techniques has led to the progression of DeepFake, a generative deep learning system that specializes in creating remarkably realistic facial characteristics. While this technology is revolutionizing applications for improving visual effects in TV channels, video games, and movies, it also raises worries because of its possible misuse, particularly in illegal actions like disseminating false information by impersonating public individuals. This survey explores the realm of DeepFake identification and highlights the growing interest in research employing deep neural networks (DNNs) to recognize and categorize these misleading media productions. Here, we present a thorough analysis of the Cutting-edge DeepFake generation techniques, grouping them into five key categories and summarizing face picture and video detection strategies based on methodology, performance metrics, types of detection, and outcomes. DeepFake models are usually tested through experiments after being trained on certain datasets. The survey investigates advancements in this field and identifies changing patterns in DeepFake datasets. The abstract also explores the task of developing a universal DeepFake detection model and discusses the related difficulties in both development and detection. The objective is to expedite the modulation of deep learning for enhancing techniques in detecting DeepFakes in both facial images and videos.

show abstract

Section: Literature Surveymentioning

confidence: 99%

“…[7]. Recently, Vision Transformers have gained popularity in computer vision, and some interesting solutions for deepfake detection have emerged, such as combining Transformers with convolutional networks or using a pretrained EfficientNet with Vision Transformers.…”

mentioning

confidence: 99%

Survey: Analysis and Detection of Deepfake in Multimedia Through Advanced Deep Learning Approaches

2024

IRJMETS

View full text Add to dashboard Cite

show abstract

“…The worries about Deepfake technology are discussed by NORAH M. ALNAIM [1] ZAYNAB M. ALMUTAIRI. Problematic worries were particularly heightened by the widespread use of face masks during the global health crisis.…”

Section: Related Wordmentioning

confidence: 99%

“…The development of computer-generated editing software in recent years has made it simpler than ever to create and alter audiovisual assets [1]. Misinformation spreading has become much more possible, particularly with the emergence of since Deepfake.…”

Section: Introductionmentioning

confidence: 99%

Video Morphing Attack Detection Using Convolutional Neural Networks On Deep Fake Detection Algorithm

2024

eatp

View full text Add to dashboard Cite

A method called deepfake produces fake video and films with artificial or substituted faces. Deepfakes are turning into a worrying societal phenomenon because they may be used maliciously to spread harmful information, fabricate electronic convincing proof, make fake political news, and even participate in online harassment and fraud. Regarding the fight against the ubiquitous threat provided by deepfake videos, our suggested technique, named "Video Morphing Attack Detection Using CNN," is a stronghold. We provide our system the capacity to model temporal relationships across sequences and extract complex characteristics from video frames by integrating the ResNeXt-50 and LSTM neural network designs, respectively. Our method effectively detects abnormalities suggestive of video morphing assaults via forward propagation and SoftMax activation. We guarantee strong detection performance while maintaining the veracity and integrity of visual information by utilizing dynamic face localization and specific assessment measures. Our system provides a comprehensive solution to reduce the negative impacts of deep fake manipulation in visual media, including vital functionalities for picture conversion, prediction creation, and data pretreatment. Convolutional neural network architecture ResNeXt-50 is a member of the ResNeXt family, which was first presented as an advancement of the ResNet design. To overcome certain constraints of conventional convolutional neural networks (CNNs), ResNeXt aims to achieve state-of-the-art performance in image classification tasks while managing intricate visual input. The "50" in ResNeXt-50 stands for the network's depth or the total number of layers it has. ResNeXt-50 comprises 50 layers in total, comprising fully connected, pooling, and convolutional layers.

show abstract

“…RELATED WORKS N. M. Alnaim and other in [4] discusses the modern Deepfakes are becoming harder to detect, which makes the issue more crucial to address. Large-scale politics, crime, personal safety, security, and society are all impacted by this technology.…”

Section: IImentioning

confidence: 99%

An In Depth Survey on Biometric ATM Handling through Fingerprint and Face Recognition using Deep Learning

Ghuge,

Avhad,

Burkul

et al. 2023

IJRASET

View full text Add to dashboard Cite

The achievement of greater ease and dependability has been made possible by India's technical advancements. The banking industry has also prospered, achieving notable improvements that have benefited the consumer. Automated Teller Machines (ATMs) have transformed transaction capabilities and decreased the likelihood of human error. Cash can always be dispensed and deposited via ATMs. This can be done with the bank-issued cards, which make integration considerably simpler. However, there has been a rise in card theft and fraudulent transactions, which compromises the dependability and security of ATMs. Consequently, rather than recognizing the card as is the case with the current model, a methodology that identifies the person during the transaction is required to increase the security and dependability of Automated Teller Machines. Implementing a biometric authentication system will be necessary to realize user identification through a virtual ATM strategy. In order to create a very reliable and secure virtual ATM, this method covers the usage of face recognition in addition to fingerprint recognition using live streaming, Channel Boosted Convolutional Neural Networks, and One Time Password implementation. The research directives to come will provide a detailed explanation of the strategy.

show abstract

DFFMD: A Deepfake Face Mask Dataset for Infectious Disease Era With Deepfake Detection Algorithms

Cited by 22 publications

References 45 publications

Survey: Analysis and Detection of Deepfake in Multimedia Through Advanced Deep Learning Approaches

Survey: Analysis and Detection of Deepfake in Multimedia Through Advanced Deep Learning Approaches

Video Morphing Attack Detection Using Convolutional Neural Networks On Deep Fake Detection Algorithm

An In Depth Survey on Biometric ATM Handling through Fingerprint and Face Recognition using Deep Learning

Contact Info

Product

Resources

About