Herd Mentality in Augmentation -- Not a Good Idea! A Robust Multi-stage Approach towards Deepfake Detection

Monu, Rohan Raju Dhanakshirur
10/7/2024
cs.CVcs.AI

Official code: Monu-Khicher-1/multi-stage-learning (1 star, last commit 2024-11-13).

Abstract

The rapid increase in deepfake technology has raised significant concerns about digital media integrity. Detecting deepfakes is crucial for safeguarding digital media. However, most standard image classifiers fail to distinguish between fake and real faces. Our analysis reveals that this failure is due to the model's inability to explicitly focus on the artefacts typically in deepfakes. We propose an enhanced architecture based on the GenConViT model, which incorporates weighted loss and update augmentation techniques and includes masked eye pretraining. This proposed model improves the F1 score by 1.71% and the accuracy by 4.34% on the Celeb-DF v2 dataset. The source code for our model is available at https://github.com/Monu-Khicher-1/multi-stage-learning

View on arXivView PDF

Code Implementations(1)

Monu-Khicher-1/multi-stage-learningOfficial100%

Deep fake detection Model

10PythonJul 22, 20241 years ago

Similar Papers

DeiTFake: Deepfake Detection Model using DeiT Multi-Stage Training

86% match2025

Patch-Discontinuity Mining for Generalized Deepfake Detection

86% match2025

Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection

86% match1 repo102024

Deepfake Sentry: Harnessing Ensemble Intelligence for Resilient Detection and Generalisation

86% match2024

CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection

86% match2 repos892024

DFCon: Attention-Driven Supervised Contrastive Learning for Robust Deepfake Detection

85% match2025

Cite this paper

@article{monu2024herd,
  title  = {Herd Mentality in Augmentation -- Not a Good Idea! A Robust Multi-stage Approach towards Deepfake Detection},
  author = {Monu and Rohan Raju Dhanakshirur},
  year   = {2024},
  eprint = {2410.05466},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.05466v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.05466.svg)](https://codeofpaper.com/paper/2410.05466)

Discussion