R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection

2026-04-19

AI Summary

This work addresses the challenging problem of reference-free, multi-type face manipulation detection in single images by proposing a novel approach that integrates high-frequency Laplacian residual statistics with a frozen large-scale Vision Transformer. The method enhances sensitivity to local fusion artifacts while preserving semantic context through two key components: a residual-statistics-gated low-rank adapter (R-FLoRA) and feature-level residual affine modulation (Res-FiLM). Additionally, a residual contrastive alignment loss is introduced to improve cross-domain generalization. Evaluated on four ICAO-compliant datasets, the proposed method significantly outperforms nine state-of-the-art S-MAD techniques, demonstrating superior accuracy, strong generalization capability, real-time efficiency, and high interpretability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Manipulation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Face morphing attacks pose a substantial risk to the reliability of face recognition systems used in passport issuance, border control, and digital identity verification. Detecting morphing attacks from a single facial image remains challenging owing to the lack of a trusted reference and the diversity of attack generation methods. This paper presents a new Single-Image Face Morphing Attack Detection (S-MAD) framework that integrates high-frequency Laplacian residual statistics with representations from a frozen, foundation-scale vision transformer. The approach employs residual-statistic-gated low-rank adapters (R-FLoRA) and feature-wise residual fusion (Res-FiLM) to enhance sensitivity to local morphing artefacts while preserving the semantic context of the backbone. A novel residual-contrastive alignment loss further regularises the fused token space, improving discrimination under unseen morphing conditions. Comprehensive experiments on four ICAO-compliant datasets, encompassing seven morph generation techniques, demonstrate that the proposed method consistently surpasses nine recent state-of-the-art S-MAD algorithms in detection accuracy and cross-domain (or dataset) generalisation. With a frozen backbone and minimal trainable parameters, the model achieves real-time efficiency and interpretability, making it suitable for real-life scenarios in biometric verification systems.

Problem

• Face Morphing Attack
• Single-Image Detection
• Biometric Security
• Morphing Artefacts
• Face Recognition

Innovation

• R-FLoRA
• Residual-Statistic-Gated Low-Rank Adaptation
• Single-Image Face Morphing Attack Detection
• Res-FiLM
• Residual-Contrastive Alignment Loss