Exposing deepfakes using a deep multilayer perceptron – convolutional neural network model

Kolagati, Santosh; Priyadharshini, T. Chindrella; Rajam, V. Mary Anita

doi:10.1016/j.jjimei.2021.100054

Cited by 44 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments show that DeepFD effectively detected 94.7% of fake images made by advanced GANs. Kolagati et al [20] constructed a deep hybrid neural network model to detect deep-fake videos. The facial landmarks detection is used to obtain information on a wide range of facial characteristics from the videos.…”

Section: Deepfake Creation and Detection Methodsmentioning

confidence: 99%

Analysis of the current state of deepfake techniques-creation and detection methods

Abu-Ein

Al-Hazaimeh

Dawood

et al. 2022

IJEECS

View full text Add to dashboard Cite

Deep learning has effectively solved complicated challenges ranging from large data analytics to human level control and computer vision. However, deep learning has been used to produce software that threatens privacy, democracy, and national security. Deepfake is one of these new applications backed by deep learning. Fake images and movies created by Deepfake algorithms might be difficult for people to tell apart from real ones. This necessitates the development of tools that can automatically detect and evaluate the quality of digital visual media. This paper provides an overview of the algorithms and datasets used to build deepfakes, as well as the approaches presented to detect deepfakes to date. By reviewing the background of deepfakes methods, this paper provides a complete overview of deepfake approaches and promotes the creation of new and more robust strategies to deal with the increasingly complex deepfakes.

show abstract

Section: Deepfake Creation and Detection Methodsmentioning

confidence: 99%

Analysis of the current state of deepfake techniques-creation and detection methods

Abu-Ein

Al-Hazaimeh

Dawood

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“… Roy et al (2022) first trained attention on the dataset to get the most prominent features of the video and then used I3D, 3D ResNet, and 3D ResNeXt to detect deepfakes. Kolagati, Priyadharshini & Mary Anita Rajam (2022) used the multi-layer perceptron to learn the difference between fake and real videos. Also, they used CNN to extract features.…”

Section: Methodsmentioning

confidence: 99%

Deepfake attack prevention using steganography GANs

Noreen¹,

Muneer²,

Gillani³

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Background Deepfakes are fake images or videos generated by deep learning algorithms. Ongoing progress in deep learning techniques like auto-encoders and generative adversarial networks (GANs) is approaching a level that makes deepfake detection ideally impossible. A deepfake is created by swapping videos, images, or audio with the target, consequently raising digital media threats over the internet. Much work has been done to detect deepfake videos through feature detection using a convolutional neural network (CNN), recurrent neural network (RNN), and spatiotemporal CNN. However, these techniques are not effective in the future due to continuous improvements in GANs. Style GANs can create fake videos with high accuracy that cannot be easily detected. Hence, deepfake prevention is the need of the hour rather than just mere detection. Methods Recently, blockchain-based ownership methods, image tags, and watermarks in video frames have been used to prevent deepfake. However, this process is not fully functional. An image frame could be faked by copying watermarks and reusing them to create a deepfake. In this research, an enhanced modified version of the steganography technique RivaGAN is used to address the issue. The proposed approach encodes watermarks into features of the video frames by training an “attention model” with the ReLU activation function to achieve a fast learning rate. Results The proposed attention-generating approach has been validated with multiple activation functions and learning rates. It achieved 99.7% accuracy in embedding watermarks into the frames of the video. After generating the attention model, the generative adversarial network has trained using DeepFaceLab 2.0 and has tested the prevention of deepfake attacks using watermark embedded videos comprising 8,074 frames from different benchmark datasets. The proposed approach has acquired a 100% success rate in preventing deepfake attacks. Our code is available at https://github.com/shahidmuneer/deepfakes-watermarking-technique.

show abstract

“…[4] Research of " Exposing deepfakes using a deep multilayer perceptronconvolutional neural network model" by Santosh kolagati, thenuga priyadharshini, V. Mary anita rajam, (2022) discusses a hybrid system proposed for screening deepfake videos with limited computational resources and at a relatively faster speed. [5] "Fake face image detection using feature network" by D. Jayaram, M. Venu gopalachari, S.Rakesh, J. Shiva sai, and G. Kiran kumar, (2022) explains about the framework uses convolution neural networks and pairwise learning to differentiate fabricated parts of the image from genuine ones. [6] Another Research "Deepfakes detection across generations: analysis of facial regions, fusion, And performance evaluation" by Ruben tolosana, sergio romero-tapiador, ruben vera-rodriguez,ester gonzalez-sosa, julian fierrez, (2022) mentions that the second generation of databases has successfully improved various aspects, such as considering different acquisition scenarios, light conditions, distances from the camera, and pose variations.…”

Section: Literature Surveymentioning

confidence: 99%

“…As the landscape of audio analytics continues to evolve, our Voice Detection System stands poised to lead the way, setting new standards for accuracy, reliability, and innovation. [5]…”

Section: Introductionmentioning

confidence: 99%

Fake Voice Detection System

et al. 2024

IJFMR

View full text Add to dashboard Cite

This research presents an advanced Voice Detection System tailored for cutting-edge audio analytics applications. Utilizing a fusion of artificial intelligence and intricate algorithms, the system excels in recognizing a diverse range of voice characteristics and subtleties. Its architecture integrates machine learning for continuous improvement and acoustic signal processing for robust performance in varying environments. The system's adaptability and scalability make it compatible with diverse infrastructures, promising seamless integration and expansion. This paper offers a detailed exploration of the system's design, theoretical foundations, and real-world applications. Aimed at stakeholders in security and communication sectors, it serves as a comprehensive guide to understanding the potential impact and implementation strategies of this innovative technology.

show abstract

Exposing deepfakes using a deep multilayer perceptron – convolutional neural network model

Cited by 44 publications

References 7 publications

Analysis of the current state of deepfake techniques-creation and detection methods

Analysis of the current state of deepfake techniques-creation and detection methods

Deepfake attack prevention using steganography GANs

Fake Voice Detection System

Contact Info

Product

Resources

About