2022
DOI: 10.18280/ts.390330
|View full text |Cite
|
Sign up to set email alerts
|

Deepfakes Classification of Faces Using Convolutional Neural Networks

Abstract: In the recent years, petabytes of data is being generated and uploaded online every second. To successfully detect fake contents, a deepfake detection technique is used to determine whether the uploaded content is real or fake. In this paper, a convolutional neural network-based model is proposed to detect the fake face images. The generative adversarial networks and data augmentation are used to generate the face dataset for real and fake face classification. Transfer learning techniques from pretrained deep … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
9
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
2
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 14 publications
(9 citation statements)
references
References 35 publications
0
9
0
Order By: Relevance
“…A deepfake, while it can be either a photo or a video, allows for a nefarious actor to replace his or her face with a computer-generated version of an authentic person's face. [23] aims to classify deepfakes using a CNN model that utilizes multiple different streams to perform classification via ensemble voting. [23] evaluates their model on multiple datasets, including the one used in this study, the 140k Real and Fake Faces dataset.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…A deepfake, while it can be either a photo or a video, allows for a nefarious actor to replace his or her face with a computer-generated version of an authentic person's face. [23] aims to classify deepfakes using a CNN model that utilizes multiple different streams to perform classification via ensemble voting. [23] evaluates their model on multiple datasets, including the one used in this study, the 140k Real and Fake Faces dataset.…”
Section: Introductionmentioning
confidence: 99%
“…[23] aims to classify deepfakes using a CNN model that utilizes multiple different streams to perform classification via ensemble voting. [23] evaluates their model on multiple datasets, including the one used in this study, the 140k Real and Fake Faces dataset. Three CNN models are developed, with two being some of the same pre-trained models seen in the previous study.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…After each model classifies the image, the voting stage is initiated. Two voting approaches are used in [23], soft voting ensemble and hard voting ensemble. Hard voting ensemble sums the votes from all the models and the image is classified based on the majority of the votes, while soft voting ensemble sums the predicted probabilities from all the models and classifies the image based on the class with the largest sum probability.…”
Section: Introductionmentioning
confidence: 99%
“…Results improved across the board, with an accuracy as high as 98.79% from the 140k Real and Fake Faces dataset. [23] displays a unique voting system while using multiple models to achieve high accuracy scores.…”
Section: Introductionmentioning
confidence: 99%