Forensics and Analysis of Deepfake Videos
Open accessAbstract
The spread of smartphones with high quality digital cameras in combination with easy access to a myriad of software apps for recording, editing and sharing videos and digital images in combination with deep learning AI platforms has spawned a new phenomenon of faking videos known as Deepfake. We design and implement a deep-fake detection model with mouth features (DFT-MF), using deep learning approach to detect Deepfake videos by isolating, analyzing and verifying lip/mouth movement. Experiments conducted against datasets that contain both fake and real videos showed favorable classification performance for DFT-MF model especially when compared with other work in this area.
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?
Zhang et al. used the bag of words method to extract a set of compact features and fed it into various classifiers such as SVM, random forest and multi-layer perceptrons for discriminating swapped face images from the genuine.
“Zhang et al. [78] used the bag of words method to extract a set of compact features and fed it into various classifiers such as SVM [79], random forest (RF) [80] and multi-layer perceptrons (MLP) [81] for discriminat- ing swapped face images from the genuine.”
From Deep learning for deepfakes creation and detection: A survey (2022) · cites this paper as [80]
The citation lists haven’t been fetched yet
References 23 · Cited by 102
- Authors
- Jafar, M. T., Ababneh, M., Al-Zoube, M., & Elhassan, A.
- Affiliations
- Princess Sumaya University for Technology (JO)
- Venue
- 2020 11th International Conference on Information and Communication Systems (ICICS)
- Publisher
- IEEE
- Published
- 2020-04
- Pages
- 053-058
- OpenAlex
- W3023887666
- Cited by
- 102
- References
- 23
- Citations by year
- 2026: 7 · 2025: 10 · 2024: 25 · 2023: 20 · 2022: 22 · 2021: 16 · 2020: 2
- FWCI
- 4.63
- Type
- conference paper
- Language
- en
- Open access
- green
- figshare.com
- Licence
- Locations
- International Conference on Information and Communication Systems (ICICS) (publishedVersion)
- Figshare (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfake detection, deepfake videos, video forgery, deep learning classification
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
