A hierarchical feature selection strategy for deepfake video detection

Mohiuddin, Sk; Sheikh, Khalid Hassan; Malakar, Samir; Velásquez, Juan D.; Sarkar, Ram

doi:10.1007/s00521-023-08201-z

Cited by 11 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…À critério de curiosidade, na literatura mais recente de detecc ¸ão de deepfakes, usando as bases Celeb-df e Faceforencis++, observa-se que os autores [Mohiuddin et al 2023] criaram um modelo de machine learning que usa a técnica de selec ¸ão das características hierárquicas, para comparar a acurácia desse modelo em cada base de dados, seja Celeb-DF ou Faceforencis++, em relac ¸ão a outras literaturas. [Mohiuddin et al 2023] utilizaram 1.416 frames reais e 9.262 fakes para Celeb-DF. Já para o Faceforencis, os autores contaram com 3.294 frames reais e 3.176 fakes.…”

Section: Análise Das Bases De Dados (Estatística E Eye-tracking)unclassified

“…Em ambas as bases de dados, todos os frames foram divididos em treino, validac ¸ão e teste. Ao longo do trabalho, [Mohiuddin et al 2023] descobriram a acurácia de 99,35% e 99,16% para ambas as bases de dados, respectivamente. Diferentemente dessa literatura, pode observar, portanto, que a principal vantagem deste estudo é a pesquisa com um conjunto limitado de amostras e com acurácias encontradas no Sobel semelhantes a esse modelo.…”

Section: Análise Das Bases De Dados (Estatística E Eye-tracking)unclassified

See 1 more Smart Citation

Sobel filter and linear classification for deepfake analysis of faces

Tamanaka,

Thomaz

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

Through artificial intelligence (AI) techniques, deepfakes (deep learning + fakes) are created. Currently, almost six years after this topic's popularization, some people have been using AI algorithms to change, for example, face. In this scenario, this article proposes to identify the most discriminating characteristics, based on the multivariate statistical learning techniques, with and without the Sobel filter. Complementarily, we aim to analyze the areas that humans have visually identified as relevant to detect a deepfake. The results show that the statistical model (PCA plus MLDA) combined with the Sobel filter correctly classified most of the images, highlighting the regions that discriminate a deepfake.

show abstract

Section: Análise Das Bases De Dados (Estatística E Eye-tracking)unclassified

Sobel filter and linear classification for deepfake analysis of faces

Tamanaka,

Thomaz

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

show abstract

Uncovering visual attention-based multi-level tampering traces for face forgery detection

Yadav,

Gupta,

Vishwakarma

2023

SIViP

View full text Add to dashboard Cite

A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models

Heidari,

Navimipour,

Dag

et al. 2024

Cogn Comput

View full text Add to dashboard Cite

In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL and blockchain technology, we address a critical need for media authenticity and security. As the threat of deepfake videos continues to grow, our comprehensive solution provides an effective means to protect the integrity and trustworthiness of visual media, with far-reaching implications for both industry and society. This work stands as a significant step toward countering the deepfake menace and preserving the authenticity of visual content in a rapidly evolving digital landscape.

show abstract

A hierarchical feature selection strategy for deepfake video detection

Cited by 11 publications

References 53 publications

Sobel filter and linear classification for deepfake analysis of faces

Sobel filter and linear classification for deepfake analysis of faces

Uncovering visual attention-based multi-level tampering traces for face forgery detection

A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models

Contact Info

Product

Resources

About