Emergent Morphing Attack Detection in Open Multi-modal Large Language Models

TL;DR

This paper demonstrates that open-source multimodal large language models can effectively detect face morphing attacks in a zero-shot setting, outperforming specialized models and revealing new forensic capabilities.

Contribution

First systematic zero-shot evaluation of open-source MLLMs for face morphing attack detection, showing their strong discriminative ability without fine-tuning.

Findings

MLLMs show non-trivial morphing detection ability without training.

LLaVA1.6-Mistral-7B surpasses task-specific MAD baselines by at least 23% EER.

Multimodal pretraining encodes facial inconsistencies for forensic analysis.

Abstract

Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models (MLLMs) have demonstrated strong visual-linguistic reasoning, but their potential in biometric forensics remains underexplored. In this paper, we present the first systematic zero-shot evaluation of open-source MLLMs for single-image MAD, using publicly available weights and a standardized, reproducible protocol. Across diverse morphing techniques, many MLLMs show non-trivial discriminative ability without any fine-tuning or domain adaptation, and LLaVA1.6-Mistral-7B achieves state-of-the-art performance, surpassing highly competitive task-specific MAD baselines by at least 23% in terms of equal error rate (EER). The results indicate that multimodal pretraining can implicitly encode fine-grained facial inconsistencies indicative of morphing artifacts, enabling zero-shot forensic sensitivity. Our findings position open-source MLLMs as reproducible, interpretable, and competitive foundations for biometric security and forensic image analysis. This emergent capability also highlights new opportunities to develop state-of-the-art MAD systems through targeted fine-tuning or lightweight adaptation, further improving accuracy and efficiency while preserving interpretability. To support future research, all code and evaluation protocols will be released upon publication.