MétaCan
Menu
Back to cohort

VeriFace: Lightweight CNN Feature Extractors for Fast Deepfake Image Authentication

2025· article· W7140905604 on OpenAlexaff
Lokesh Khedekar, Smita Mande, Ajay S. Chhajed, Tejas Kedar, Kaustubh Kelgandre, Atharva Kassa

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsFeature (linguistics)Image (mathematics)Authentication (law)Pattern recognition (psychology)Feature extraction

Abstract

fetched live from OpenAlex

A lightweight convolutional neural network pipeline is presented in this paper for the purposes of deep fake image detection which emphasizes structured training, practical deployment and confidence estimation for real world scenarios. The method employs balanced datasets for training, standard methods for pre-processing and data augmentation of images and performance is measured in terms of accuracy, precision, recall and confusion matrix analysis to avoid overfitting and maintain generalizability across broadcasting datasets. The network architecture uses compact feature extraction and binary classification head as a binary classification system and employs probability tuning in order to provide reliable confidence scores for decision support. A web ready interface is built to allow sub second prediction of lone images via optimised pre-processing and model loading stages therefore allowing seamless end to end operation. Experimental results indicate strong classification performance attained for limited input resolution and number of epochs during training, supporting the designs made with respect to reliability, speed and deployability as misinformation reduction mechanisms.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.011
Threshold uncertainty score0.035

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0110.004

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 head0.259
Teacher spread0.250 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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 routes1
Has abstractyes

Explore more

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