StableMorph: High-Quality Face Morph Generation with Stable Diffusion

2025-11-11

AI Summary

Existing facial morphing attack generation methods produce low-quality images—characterized by blurriness, artifacts, and structural distortions—rendering them easily detectable and inadequate for simulating realistic threats, thereby limiting the evaluation of Morphing Attack Detection (MAD) systems. To address this, we propose a diffusion-based face fusion framework built upon Stable Diffusion, incorporating facial prior guidance and fine-grained attribute control to generate high-resolution, natural, artifact-free full-head portrait morphs. Our method significantly enhances attack stealthiness and visual fidelity: generated morphs exhibit structural plausibility, sharp texture detail, and strong identity ambiguity, closely approximating authentic human faces. Empirically, they successfully evade state-of-the-art face recognition systems and pose greater challenges to existing MAD detectors. This work establishes a more realistic and rigorous benchmark for biometric security assessment.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Face morphing attacks threaten the integrity of biometric identity systems by enabling multiple individuals to share a single identity. To develop and evaluate effective morphing attack detection (MAD) systems, we need access to high-quality, realistic morphed images that reflect the challenges posed in real-world scenarios. However, existing morph generation methods often produce images that are blurry, riddled with artifacts, or poorly constructed making them easy to detect and not representative of the most dangerous attacks. In this work, we introduce StableMorph, a novel approach that generates highly realistic, artifact-free morphed face images using modern diffusion-based image synthesis. Unlike prior methods, StableMorph produces full-head images with sharp details, avoids common visual flaws, and offers unmatched control over visual attributes. Through extensive evaluation, we show that StableMorph images not only rival or exceed the quality of genuine face images but also maintain a strong ability to fool face recognition systems posing a greater challenge to existing MAD solutions and setting a new standard for morph quality in research and operational testing. StableMorph improves the evaluation of biometric security by creating more realistic and effective attacks and supports the development of more robust detection systems.

Problem

• Generating realistic artifact-free face morphs for security testing
• Addressing limitations of blurry and detectable existing morph generation
• Enhancing biometric system evaluation with high-quality attack simulations

Innovation

• Uses diffusion-based image synthesis for morphing
• Generates full-head images with sharp details
• Provides control over visual attributes