MétaCan
Menu
Back to cohort

A High-Fidelity Partial Face Manipulation Dataset for Enhanced Deepfake Detection

2024· article· en· W4399882028 on OpenAlexaff
Kaitai Tong, Junbin Zhang, Yixiao Wang, Hamidreza Tohidypour, Panos Nasiopoulos

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsFace (sociological concept)Computer scienceFidelityArtificial intelligenceHigh fidelityMachine learningEngineering

Abstract

fetched live from OpenAlex

Deepfake technology has already impacted the integrity of news and may grow to hugely destructive political and social force. The realistic and convincing nature of deepfakes poses a threat to the authenticity of information, alarming individuals and organizations. While many studies have explored the issue of deepfakes, the majority of them have focused on swapping entire faces rather than partially manipulating them, which can be more difficult to detect. In this paper, we introduce a high-fidelity partially manipulated face dataset, aiming to fill the gap in the existing deepfake research by providing a comprehensive benchmark for partially manipulated face detection. Our dataset includes a diverse set of partially manipulated faces which is generated from high-quality facial images. Our proposed alignment pipeline ensures that the partially manipulated faces may be realistically integrated into the original images, providing a more challenging evaluation environment for deepfake detection models. Both objective and subjective evaluations of our proposed dataset have shown promising results, indicating its potential to become a significant benchmark for partially manipulated face detection.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.971
Threshold uncertainty score0.277

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
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 head0.031
GPT teacher head0.292
Teacher spread0.261 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
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

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicFace recognition and analysisFrench-language works237,207