Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation

H. Zen, R. Wagh, M. Wanderley, G. Bicalho, R. Park, M. Sun, R. Palacios, L. Carvalho, G. Rinaldo, A. Gupta

Computers Vol. 14, nº. 6, pp. 225

Summary:

Deepfake images, synthetic images created using digital software, continue to present a serious threat to online platforms. This is especially relevant for biometric verification systems, as deepfakes that attempt to bypass such measures increase the risk of impersonation, identity theft and scams. Although research on deepfake image detection has provided many high-performing classifiers, many of these commonly used detection models lack generalizability across different methods of deepfake generation. For companies and governments fighting identify fraud, a lack of generalization is challenging, as malicious actors may use a variety of deepfake image-generation methods available through online wrappers. This work explores if combining multiple classifiers into an ensemble model can improve generalization without losing performance across different generation methods. It also considers current methods of deepfake image generation, with a focus on publicly available and easily accessible methods. We compare our framework against its underlying models to show how companies can better respond to emerging deepfake generation methods.

Spanish layman's summary:

La detección de imágenes deepfake es un componente muy relevante para reducir la suplantación, robo de identidad y engaños. Este trabajo combina varios clasificadores en un ensemble para mejorar la capacidad de generalización ante diferentes métodos de generación de deepfake.

English layman's summary:

Deepfake image detection is a crucial component to mitigate impersonation, identity theft, and scams. This work explores the combination of multiple classifiers into an ensemble model to improve generalization across different deepfake generation methods.

Keywords: deepfakes; biometric verification systems; generalization; ensemble learning; deepfake detection model

JCR-JIF Impact Factor and WoS quartile: 5,200 - Q2 (2025)

DOI reference: https://doi.org/10.3390/computers14060225

Published on paper: June 2025.

Published on-line: June 2025.

Citation:
H. Zen, R. Wagh, M. Wanderley, G. Bicalho, R. Park, M. Sun, R. Palacios, L. Carvalho, G. Rinaldo, A. Gupta, "Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation", Computers, Vol. 14, nº. 6, pp. 225, June 2025. [Online: June 2025] doi: 10.3390/computers14060225