LAMM-ViT: AI Face Detection via Layer-Aware Modulation of Region-Guided Attention

TL;DR

LAMM-ViT is a novel vision transformer that uses layer-aware modulation and region-guided attention to improve the detection of AI-synthetic faces across diverse generative models, outperforming previous methods.

Contribution

The paper introduces LAMM-ViT, a transformer architecture with dynamic layer-specific modulation and region-guided attention for robust facial forgery detection.

Findings

Achieves 94.09% accuracy, outperforming state-of-the-art by 5.45%.

Attains 98.62% average precision, surpassing previous methods.

Demonstrates strong generalization across different generative models.

Abstract

Detecting AI-synthetic faces presents a critical challenge: it is hard to capture consistent structural relationships between facial regions across diverse generation techniques. Current methods, which focus on specific artifacts rather than fundamental inconsistencies, often fail when confronted with novel generative models. To address this limitation, we introduce Layer-aware Mask Modulation Vision Transformer (LAMM-ViT), a Vision Transformer designed for robust facial forgery detection. This model integrates distinct Region-Guided Multi-Head Attention (RG-MHA) and Layer-aware Mask Modulation (LAMM) components within each layer. RG-MHA utilizes facial landmarks to create regional attention masks, guiding the model to scrutinize architectural inconsistencies across different facial areas. Crucially, the separate LAMM module dynamically generates layer-specific parameters, including mask weights and gating values, based on network context. These parameters then modulate the behavior of RG-MHA, enabling adaptive adjustment of regional focus across network depths. This architecture facilitates the capture of subtle, hierarchical forgery cues ubiquitous among diverse generation techniques, such as GANs and Diffusion Models. In cross-model generalization tests, LAMM-ViT demonstrates superior performance, achieving 94.09% mean ACC (a +5.45% improvement over SoTA) and 98.62% mean AP (a +3.09% improvement). These results demonstrate LAMM-ViT's exceptional ability to generalize and its potential for reliable deployment against evolving synthetic media threats.