Improving Video Deepfake Detection: A DCT-Based Approach with Patch-Level Analysis

Luca Guarnera, Salvatore Manganello, Sebastiano Battiato
10/17/2023
cs.CVeess.IV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

A new algorithm for the detection of deepfakes in digital videos is presented. The I-frames were extracted in order to provide faster computation and analysis than approaches described in the literature. To identify the discriminating regions within individual video frames, the entire frame, background, face, eyes, nose, mouth, and face frame were analyzed separately. From the Discrete Cosine Transform (DCT), the Beta components were extracted from the AC coefficients and used as input to standard classifiers. Experimental results show that the eye and mouth regions are those most discriminative and able to determine the nature of the video under analysis.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

CUPID: Reconstructing UV Texture Maps for Interpretable Person-of-Interest Deepfake Detection

89% match2026

Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories

89% match2024

Impact of Video Processing Operations in Deepfake Detection

89% match2023

Unmasking Deepfake Faces from Videos Using An Explainable Cost-Sensitive Deep Learning Approach

89% match1 repo102023

FakeParts: a New Family of AI-Generated DeepFakes

89% match2025

GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer

89% match2 repos1112023

Cite this paper

@article{guarnera2023improving,
  title  = {Improving Video Deepfake Detection: A DCT-Based Approach with Patch-Level Analysis},
  author = {Luca Guarnera and Salvatore Manganello and Sebastiano Battiato},
  year   = {2023},
  eprint = {2310.11204},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.11204v2}
}

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/2310.11204.svg)](https://codeofpaper.com/paper/2310.11204)

Discussion