LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery Detection

2026-04-12

AI Summary

Existing methods for cross-domain face forgery detection suffer from limited generalization and high computational costs, hindering deployment on resource-constrained devices. This work proposes LRD-Net, a lightweight network featuring a novel frequency-guided sequential architecture. It employs a multi-scale wavelet-guided module to generate attention signals that dynamically modulate a MobileNetV3 spatial backbone, while integrating real-face-centric representation learning with drift regularization to enable efficient joint frequency-spatial modeling. Evaluated on the DiFF benchmark, the proposed method achieves state-of-the-art accuracy with only 2.63 million parameters—approximately one-ninth of existing approaches—while offering over 8× faster training and nearly 10× faster inference, striking an exceptional balance between performance and efficiency suitable for real-time mobile applications.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The rapid advancement of diffusion-based generative models has made face forgery detection a critical challenge in digital forensics. Current detection methods face two fundamental limitations: poor cross-domain generalization when encountering unseen forgery types, and substantial computational overhead that hinders deployment on resource-constrained devices. We propose LRD-Net (Lightweight Real-centered Detection Network), a novel framework that addresses both challenges simultaneously. Unlike existing dual-branch approaches that process spatial and frequency information independently, LRD-Net adopts a sequential frequency-guided architecture where a lightweight Multi-Scale Wavelet Guidance Module generates attention signals that condition a MobileNetV3-based spatial backbone. This design enables effective exploitation of frequency-domain cues while avoiding the redundancy of parallel feature extraction. Furthermore, LRD-Net employs a real-centered learning strategy with exponential moving average prototype updates and drift regularization, anchoring representations around authentic facial images rather than modeling diverse forgery patterns. Extensive experiments on the DiFF benchmark demonstrate that LRD-Net achieves state-of-the-art cross-domain detection accuracy, consistently outperforming existing methods. Critically, LRD-Net accomplishes this with only 2.63M parameters - approximately 9x fewer than conventional approaches - while achieving over 8x faster training and nearly 10x faster inference. These results demonstrate that robust cross-domain face forgery detection can be achieved without sacrificing computational efficiency, making LRD-Net suitable for real-time deployment in mobile authentication systems and resource-constrained environments.

Problem

• face forgery detection
• cross-domain generalization
• computational overhead
• resource-constrained devices
• digital forensics

Innovation

• Lightweight architecture
• Frequency-guided attention
• Real-centered learning
• Cross-domain generalization
• Face forgery detection