Light-weight 3DCNN for DeepFakes, FaceSwap and Face2Face facial forgery detection

Kohli, Aditi; Gupta, Abhinav

doi:10.1007/s11042-022-12778-3

Cited by 7 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL networks (DNN) have accelerated and simpli ed the process of creating compelling synthetic images and movies. It involves altering a person's video or image with another person's image using DL algorithms such as the general adversarial network (GAN) [6] [7]. Face swap is a crucial step in establishing a fake video as it involves the exchange of a source that challenges a victim's face while preserving the victim's initial movements and verbalization spoofs.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Deepfake Detection Using Robust Deep Learning Approch

Qadir

Mahum

El-Meligy

et al. 2023

Preprint

View full text Add to dashboard Cite

The creation and manipulation of synthetic images have evolved rapidly, creating serious concerns about their effects on society. Although there have been various attempts to identify deep fake videos, these approaches are not universal. Identifying these misleading deepfakes is the first step in preventing them from following on social media sites. We introduce a unique deep-learning technique to identify fraudulent clips. Most deepfake identifiers currently focus on identifying face exchange, lip synchronous, expression modification, puppeteers, and other factors. However, exploring a consistent basis for all forms of fake video and images in real-time forensics is challenging. We propose a hybrid technique that takes input from videos of successive targeted frames, then feeds these to the ResNet-Swish-BiLSTM, an optimized convolutional BiLSTM-based residual network for training and classification. This proposed method helps identify artifacts in deepfake images that do not seem real. To assess the robustness of our proposed model, we used the open deepfake detection challenge dataset (DFDC) and Face Forensics deepfake collections (FF++.) We achieved 96.23% accuracy when using the FF + + digital record. In contrast, we attained 78.33% accuracy using the aggregated records from FF + + and DFDC. We performed extensive experiments and believe that our proposed method provides more significant results than existing techniques.

show abstract

Section: Introductionmentioning

confidence: 99%