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

TL;DR

LRD-Net is a lightweight, real-centered face forgery detection model that excels in cross-domain accuracy and efficiency, suitable for resource-limited devices.

Contribution

It introduces a novel frequency-guided architecture with real-centered learning, achieving state-of-the-art results with significantly fewer parameters and faster inference.

Findings

Achieves state-of-the-art cross-domain detection accuracy.

Uses only 2.63 million parameters, about 9 times fewer than existing methods.

Provides over 8 times faster training and nearly 10 times faster inference.

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.