ExDDV: A New Dataset for Explainable Deepfake Detection in Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hondru, Vlad, Hogea, Eduard, Onchis, Darian, Ionescu, Radu Tudor
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911285673721856
author Hondru, Vlad
Hogea, Eduard
Onchis, Darian
Ionescu, Radu Tudor
author_facet Hondru, Vlad
Hogea, Eduard
Onchis, Darian
Ionescu, Radu Tudor
contents The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14421
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ExDDV: A New Dataset for Explainable Deepfake Detection in Video
Hondru, Vlad
Hogea, Eduard
Onchis, Darian
Ionescu, Radu Tudor
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Multimedia
The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.
title ExDDV: A New Dataset for Explainable Deepfake Detection in Video
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Multimedia
url https://arxiv.org/abs/2503.14421