Deepfakes Detection Techniques Using Deep Learning: A Survey

Almars, Abdulqader M.

doi:10.4236/jcc.2021.95003

Cited by 72 publications

(26 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the United States and Asian societies, many women are also victimized by deep fake technologies. The harmful use of deep fakes can significantly impact our culture and increase misleading information, especially on social media [ 6 ]. However, because of the negative impacts on different individuals and organizations, deepfakes have been a significant threat to our current generation.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network

Shad

Rizvee

Roza

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Generation Z is a data-driven generation. Everyone has the entirety of humanity’s knowledge in their hands. The technological possibilities are endless. However, we use and misuse this blessing to face swap using deepfake. Deepfake is an emerging subdomain of artificial intelligence technology in which one person’s face is overlaid over another person’s face, which is very prominent across social media. Machine learning is the main element of deepfakes, and it has allowed deepfake images and videos to be generated considerably faster and at a lower cost. Despite the negative connotations associated with the phrase “deepfakes,” the technology is being more widely employed commercially and individually. Although it is relatively new, the latest technological advances make it more and more challenging to detect deepfakes and synthesized images from real ones. An increasing sense of unease has developed around the emergence of deepfake technologies. Our main objective is to detect deepfake images from real ones accurately. In this research, we implemented several methods to detect deepfake images and make a comparative analysis. Our model was trained by datasets from Kaggle, which had 70,000 images from the Flickr dataset and 70,000 images produced by styleGAN. For this comparative study of the use of convolutional neural networks (CNN) to identify genuine and deepfake pictures, we trained eight different CNN models. Three of these models were trained using the DenseNet architecture (DenseNet121, DenseNet169, and DenseNet201); two were trained using the VGGNet architecture (VGG16, VGG19); one was with the ResNet50 architecture, one with the VGGFace, and one with a bespoke CNN architecture. We have also implemented a custom model that incorporates methods like dropout and padding that aid in determining whether or not the other models reflect their objectives. The results were categorized by five evaluation metrics: accuracy, precision, recall, F1-score, and area under the ROC (receiver operating characteristic) curve. Amongst all the models, VGGFace performed the best, with 99% accuracy. Besides, we obtained 97% from the ResNet50, 96% from the DenseNet201, 95% from the DenseNet169, 94% from the VGG19, 92% from the VGG16, 97% from the DenseNet121 model, and 90% from the custom model.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network

Shad

Rizvee

Roza

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Randika [30] also acknowledges Deep learning techniques as the future of fake news detection, although he is also aware that there are still several limitations to be solved through further research. Almars [4] highlights the exceptional performance of Deep learning techniques in detecting Deepfakes. However, he does not ignore the fact that the quality of Deepfakes is constantly improving, and detection techniques shall improve with them.…”

Section: Discussionmentioning

confidence: 99%

“…For example, there is research such as the one conducted by Tariq et al [37], who developed a method based on a convolutional LSTM for analyzing deepfake videos. To complement the above, there are analyses such as the one performed by Almars [4], which focused on making a compilation of the most recent proposals for automatic detection of deepfakes, both photos and videos. Table 1 explores in more detail the recent investigations regarding the use of Deep learning for fake news and deepfakes detection and the most important results obtained.…”

Section: Current Researchmentioning

confidence: 99%

Fake News Detection in Internet Using Deep Learning: A Review

Barreto

Córdova

Arana

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

The main objective of this research was to explore, from a reflexivity approach, the current state of Deep learning techniques for automatic detection of fake news on the Internet, analyzing the most important Deep learning algorithms and studies on their effectiveness in detecting distrustful information. The research methodology employed was bibliographic, documentary and descriptive. The information was collected from several scientific articles provided by indexed journals and web platforms, using keywords such as "fake news", "Deep learning" and "neural networks" for the compilation. As a result of this research, it was concluded that Deep learning techniques present a better performance than conventional methods and will be of great importance in the future of war against fake news due to their potential in automatic detection.

show abstract

“…Many businesses, including Facebook Inc., Google, and the United States Defense Advanced Research Projects Agency (DARPA), have launched a research initiative to find and eliminate deep fakes [6] and [7]. Numerous deep learning methods, including long short-term memory (LSTM), recurrent neural networks (RNN), and even hybrid approaches, have been created to detect deep fakes in images and videos, and additional research has been conducted in this area [8] and [9].…”

Section: Introductionmentioning

confidence: 99%

A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model

Ikram

Priya

Chambial

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

In the current era, many fake videos and images are created with the help of various software and new AI (Artificial Intelligence) technologies, which leave a few hints of manipulation. There are many unethical ways videos can be used to threaten, fight, or create panic among people. It is important to ensure that such methods are not used to create fake videos. An AI-based technique for the synthesis of human images is called Deep Fake. They are created by combining and superimposing existing videos onto the source videos. In this paper, a system is developed that uses a hybrid Convolutional Neural Network (CNN) consisting of InceptionResnet v2 and Xception to extract frame-level features. Experimental analysis is performed using the DFDC deep fake detection challenge on Kaggle. These deep learning-based methods are optimized to increase accuracy and decrease training time by using this dataset for training and testing. We achieved a precision of 0.985, a recall of 0.96, an f1-score of 0.98, and support of 0.968.

show abstract

Deepfakes Detection Techniques Using Deep Learning: A Survey

Cited by 72 publications

References 39 publications

[Retracted] Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network

[Retracted] Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network

Fake News Detection in Internet Using Deep Learning: A Review

A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model

Contact Info

Product

Resources

About