Intelligent multimodal face anti-spoofing detection system based on biometrics

Adaptive multimodal liveness detection framework for biometric authentication against spoofing and deepfake attacks

With the explosive growth of generative AI technologies, the threat posed by spoofing attacks and deepfake attacks on biometric authentication systems continues to grow. Traditional biometric systems rely on visual presentation and are subject to various types of presentation attacks such as replay attacks, printed photographs, and synthetic deepfake identities. This paper presents an Adaptive Multimodal Liveness Detection Framework (AMLF) to increase the strength of biometric identity systems and reduce their vulnerability to both spoofing and deepfake attacks. The framework also aims to reduce the computational costs of performing liveness detection on resource-constrained edge devices. The proposed framework uses three techniques for liveness detection across multiple biometric modalities (face, fingerprint, and iris): spatial texture analysis, temporal biometric signals, and frequency-domain artifacts. A lightweight, deep neural network architecture is used for the multimodal liveness detection process on edge devices and enables real-time liveness detection. A series of experiments conducted on publicly available datasets (FaceForensics++ , CASIA-Iris-V4, MSU-MFSD, and FVC2006) demonstrate that the proposed AMLF considerably increases the accuracy of detecting spoofing attacks over existing approaches based on deep learning methods while significantly reducing the computational costs associated with these methods. Overall, the AMLF framework provides a highly effective means to improve the capability of next generation biometric authentication systems, particularly in an edge computing environment.

Spatiotemporal attention driven framework for video-based face presentation attack detection

Digital Identity Verification Using Liveness Detection Models

A systematic framework is proposed, encompassing data acquisition, preprocessing, feature extraction, model training, and decision fusion, supported by mathematical formulations for classification, loss optimization, and evaluation metrics, offering a scalable approach for secure digital identity verification.

Multi-Biometric Fusion of Iris and Face Dynamics using Deep Learning for High-Security Human Identification

The increasing need for reliable human identification systems in secure environments has exposed the limitations of unimodal biometric systems. Individual biometric modalities, including fingerprint, face recognition, and iris scanning, are prone to noise, hardware limitations, spoofing attacks, and data acquisition errors, resulting in high false acceptance and false rejection rates. This paper presents a comprehensive framework for human identification using multi-biometric fusion of iris and face dynamics using a deep learning paradigm. By holistically combining the noise-free properties of the iris with the nonintrusive and globally accessible properties of facial features, the proposed system overcomes the fundamental limitations of unimodal biometric systems while harnessing their complementary benefits. The framework encompasses systematic data acquisition in various environmental settings, sophisticated preprocessing techniques involving normalization and augmentation, robust feature extraction using convolutional neural networks, and multi-level fusion techniques at the feature, score, and decision levels. Experimental results show that the proposed fusion strategy outperforms unimodal biometric systems in recognition accuracy, with a rate of accuracy above 99% and lower error rates. The proposed system is designed for critical applications in banking security, border protection, healthcare, and law enforcement, where identification accuracy and system integrity are paramount.

Modality-Shared Anti-Spoofing for Face and Fingerprint

Multi-modal anti-spoofing aims to differentiate live users from spoofing attacks using multiple biometric modalities during model training. While existing anti-spoofing methods often incorporate just one biometric modality, the effectiveness of attacking two or more biometric traits remains questionable. In this work, we introduce the multi-modal anti-spoofing approach to detect spoofing attacks across face and fingerprint. Our framework is built around an Angular Margin Loss (ArcFace) that increases interclass separation without disrupting cross-modal alignment, which enables reliable spoof detection across both face and fingerprint biometric characteristics. Moreover, to enhance model generalization against unseen spoof attacks, we include three adversarial attacks (i.e., FGSM, PGD, DeepFool) to evaluate our system. Extensive experiments on multi-modal benchmarks show that the proposed method not only significantly outperforms previous anti-spoofing methods but also uniquely offers the ability to handle potential attack types.

Comparative Analysis of Various Biometric Recognition along with Secure Multi-modal System

The study’s objective is to create a facial recognition system that is both lightweight and effective for secure biometric identification using MobileNetV3, and to assess how well it performs in comparison to more conventional, computationally demanding models. Group 2 (Intervention) refers to a MobileNetV3-based face recognition system with 30 samples and 98% confidence, while Group 1(control)relates to Conventional CNN based facial recognition models with 30 samples but low accuracy To guarantee high-quality inputs, data preprocessing methods like image alignment and normalization are employed. The model’s judgment are interpreted using SHAP (Shapely Additive Explanations), which also detects biases and identifies real inputs from fake attempts, such as images and movies, liveness detection techniques are used. When compared to conventional models, the MobileNetV3-based system achieved a far higher accuracy of 95% in facial recognition tasks. The system showed a Multi-Modal with 98% accuracy and low latency, which makes it appropriate for real-time applications. Transparency was greatly increased by SHAP-driven insights, which offered concise justifications for model choices. This study shows that the lightweight MobileNetV3-based facial recognition system outperforms conventional models in terms of accuracy, security, and explainability.