ExDDV: A New Dataset for Explainable Deepfake Detection in Video
Abstract
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent datasets such as DDL and ExDDV are explicitly designed with explainability in mind, combining binary labels, pixel-level masks, and human-generated textual descriptions.
“Recent datasets such as DDL [51] and ExDDV [52] are explicitly designed with explainability in mind, combining binary labels, pixel-level masks, and human-generated textual descriptions.”
From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [52]
ExDDV is the first dataset specifically designed for explainable video deepfake detection, providing localization masks and human annotations in the form of clicks marking artifacts and textual descriptions.
“Hondru et al. [52] released ExDDV, the first dataset specifically designed for explainable video Deepfake detection. In addition to localization masks, ExDDV provides human annotations in the form of clicks marking artifacts and textual descriptions explaining them.”
From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [52]
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
References 49 · Cited by 3
- Authors
- Hondru, V., Hogea, E., Onchiş, D., & Ionescu, R. T.
- Affiliations
- University of Bucharest (RO)
- West University of Timişoara (RO)
- Venue
- 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2026-03-06
- Pages
- 4273-4284
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W7160274414
- Cited by
- 3
- References
- 49
- Citations by year
- 2026: 2 · 2025: 1
- FWCI
- 17.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, explainable AI, video forgery, vision-language models, in-context learning, fine-tuning, misinformation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
