A Review of Deep Learning-based Approaches for Deepfake Content Detection

View on arXiv ← Back to list

Authors: Leandro A. Passos, Danilo Jodas, Kelton A. P. da Costa, Luis A. Souza Júnior, Douglas Rodrigues, Javier Del Ser, David Camacho, João Paulo Papa

Published: 2022-02-12 16:22:46+00:00

AI Summary

This paper provides a comprehensive review of deep learning-based approaches for deepfake content detection, systematically reviewing different categories of fake content detection and highlighting the advantages and drawbacks of existing works.

Abstract

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this issue, there is a pressing need to develop new computational models that can efficiently detect forged content and alert users to potential image and video manipulations. This paper presents a comprehensive review of recent studies for deepfake content detection using deep learning-based approaches. We aim to broaden the state-of-the-art research by systematically reviewing the different categories of fake content detection. Furthermore, we report the advantages and drawbacks of the examined works, and prescribe several future directions towards the issues and shortcomings still unsolved on deepfake detection.

Key findings

The review reveals that while significant progress has been made, challenges remain in developing robust and generalizable deepfake detection methods. The performance of models often varies across different datasets and deepfake generation techniques. Multimodal approaches combining audio and video show promise for improved detection accuracy.

Approach

The paper reviews existing deep learning models for deepfake detection, categorizing them by approach (CNNs, Generative Models, RNNs, Transformers) and analyzing their performance on various datasets. It also examines the datasets used in deepfake detection research.

Datasets

HOHA-based, Faceswap-GAN, UADFV, Deepfake-TIMIT, FaceForensics, FaceForensics++, Deepfake Detection Challenge (DFDC), Celeb-DF, DeeperForensics-1.0, Real and Fake Face Detection, WildDeepfake, Fake Face in the Wild

Model(s)

AlexNet, VGG16, ResNet, Xception, Inception, ResNext, Ensemble methods, Autoencoder, GAN, LSTM, GRU, Transformer, EfficientNet, InceptionResNetV2, DenseNet, MobileNet, Vision Transformer (ViT), Siamese networks, ConvGRU, BiLSTM, XceptionNet

Author countries

Brazil, Spain

← Previous