MétaCan
Menu
Back to cohort

Audio-Visual Cross-Attention for Improved Deepfake Video Detection and Forgery Localization

2025· article· W7125901270 on OpenAlexafffund
Oussama Jalleli, Yi Zhu, Tiago Henrik Falk

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsInstitut National de la Recherche Scientifique
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsRobustness (evolution)Focus (optics)ModalitiesDetectorComplementarity (molecular biology)Pattern recognition (psychology)

Abstract

fetched live from OpenAlex

With the emergence of multi-modal generative models, synthesized videos are becoming increasingly realistic, making the detection of deepfakes extremely challenging. While several video deepfake detection models have shown promising performance, their focus has been primarily on the visual modality. To overcome this limitation, we propose a dualstream framework that fuses visual and auditory information via cross-attention computed between embeddings extracted from pre-trained video and audio encoders. Additionally, we design a weakly-supervised forgery localization head that infers frame-level forgery scores from coarse segment-level labels, minimizing the need for fine-grained annotations and allowing for forgery location characterization. In this paper, we describe our preliminary results showing the proposed model outperforming state-of-the-art detectors on both frame-level localization and sequence-level deepfake detection tasks. Ongoing work focuses on investigating the complementarity between the visual and auditory modalities to improve model robustness and explainability.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.975
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.274
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicGenerative Adversarial Networks and Image SynthesisFrench-language works237,207