MétaCan
Menu
Back to cohort
Record W4387164795 · doi:10.21203/rs.3.rs-3371756/v1

A Novel Deep Learning-Based Method for Real-Time Face Spoof Detection

2023· preprint· en· W4387164795 on OpenAlexaff
Muhammad Amir Malik, Tehseen Mazhar, Inayatul Haq, Tariq Shahzad, Yazeed yaseen Ghadi, Fatma Mallek, Habib Hamam

Bibliographic record

VenueResearch Square · 2023
Typepreprint
Languageen
FieldComputer Science
TopicBiometric Identification and Security
Canadian institutionsUniversité de Moncton
Fundersnot available
KeywordsComputer scienceConvolutional neural networkArtificial intelligenceSpoofing attackFace (sociological concept)Naive Bayes classifierSupport vector machineFace detectionDeep learningFacial recognition systemReplay attackPattern recognition (psychology)Computer visionMachine learningAuthentication (law)Computer security

Abstract

fetched live from OpenAlex

Abstract Facial-based Commercial Off-The-Shelf (COTS) systems increase the success rate of spoof attacks to 70% detection accuracy. A spoof attack uses an image, video, or 3D model of a person to gain unauthorized access to a biometric system. Face spoof attacks are mostly based on common spoof vectors, print attacks, and replay attacks. This research aims to improve the detection accuracy of face spoof recognition systems by employing a hybrid model of machine learning and computer vision-based approaches. Differences, including Decision Tree, Nave Bayes, K-nearest Neighbor, Support Vector Machine, Convolutional Neural Network (CCN), and Recurrent Neural Networks are used for face spoof detection. For face spoof detection, the proposed model is a hybrid variant of the CNN-based classifier used in the proposed face spoof detection model. This study improves real-time face fake detection using machine learning and computer vision. The proposed system is based on a CNN-based classification approach with optimized hyper parameters that detect real-time face spoofing attacks using print, video, and repeat attacks, improving detection accuracy. IDIAP, USSA & and MSFD datasets are used in the simulation; the proposed model has achieved a maximum accuracy of 87.5%. Furthermore, the proposed model achieved a high sensitivity score of 92.45%, indicating that it is highly likely to be used for spoof attack detection systems in the future.

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)0.008
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.919
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0080.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.004
Science and technology studies0.0010.000
Scholarly communication0.0010.000
Open science0.0020.001
Research integrity0.0010.002
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 head0.133
GPT teacher head0.437
Teacher spread0.304 · 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
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueResearch SquareSame topicBiometric Identification and SecurityFrench-language works237,207