MorphGuard: Morph Specific Margin Loss for Enhancing Robustness to Face Morphing Attacks

2025-05-15

AI Summary

Face morphing attacks pose a significant threat to face authentication systems. To address this, this paper proposes a dual-branch classification training framework that explicitly incorporates morphed images into the training process, thereby enhancing the model’s discriminative capability between morphed and bona fide faces. The core contribution is a morph-specific margin loss, designed to mitigate label ambiguity inherent in morphed samples by enforcing class-aware decision boundaries. The framework is end-to-end trainable and requires no auxiliary detection module. Evaluated on multiple public benchmarks, the method achieves substantial improvements in robustness against morphing attacks while maintaining full compatibility with mainstream face recognition training pipelines—enabling plug-and-play deployment to strengthen existing systems’ security without architectural modification.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Face recognition has evolved significantly with the advancement of deep learning techniques, enabling its widespread adoption in various applications requiring secure authentication. However, this progress has also increased its exposure to presentation attacks, including face morphing, which poses a serious security threat by allowing one identity to impersonate another. Therefore, modern face recognition systems must be robust against such attacks. In this work, we propose a novel approach for training deep networks for face recognition with enhanced robustness to face morphing attacks. Our method modifies the classification task by introducing a dual-branch classification strategy that effectively handles the ambiguity in the labeling of face morphs. This adaptation allows the model to incorporate morph images into the training process, improving its ability to distinguish them from bona fide samples. Our strategy has been validated on public benchmarks, demonstrating its effectiveness in enhancing robustness against face morphing attacks. Furthermore, our approach is universally applicable and can be integrated into existing face recognition training pipelines to improve classification-based recognition methods.

Problem

• Enhancing robustness to face morphing attacks in recognition
• Handling ambiguity in labeling face morphs effectively
• Improving distinction between morph and bona fide samples

Innovation

• Dual-branch classification for morph ambiguity
• Incorporates morph images into training
• Improves robustness against morphing attacks