A defensive attention mechanism to detect deepfake content across multiple modalities
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?
Current multi-modal and audio-visual deepfake detectors are often based on attention-based fusion of heterogeneous data streams from multiple modalities.
“Current multi-modal deepfake detectors are often based on the attention-based fusion of heterogeneous data streams from multiple modalities.”
From Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization (2024) · cites this paper as [5]
The citation lists haven’t been fetched yet
References 42 · Cited by 16
- Authors
- Asha, S., Vinod, P., & Menon, V. G.
- Affiliations
- SCMS Group of Educational Institutions (IN)
- Cochin University of Science and Technology (IN)
- Corresponding author
- Asha, S.
- Venue
- Multimedia Systems
- Published
- 2024-02
- Volume
- 30
- Issue
- 1
- ISSN
- 0942-4962 (ISSN-L)
- 1432-1882
- OpenAlex
- W4391855470
- Cited by
- 16
- References
- 42
- Citations by year
- 2026: 4 · 2025: 9 · 2024: 3
- FWCI
- 2.25
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Multimedia Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, cross-modal attention, self-attention, audio-visual alignment, imbalanced training data
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
