LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection
This addresses the challenge of detecting increasingly realistic face forgeries, which is critical for security and media integrity, though it appears incremental as it builds on existing attention and multi-task learning approaches.
The paper tackles the problem of deepfake detection by proposing LAA-X, a framework that is robust to high-quality forgeries and generalizes to unseen manipulations, achieving competitive results with state-of-the-art methods across multiple benchmarks.
In this paper, we propose Localized Artifact Attention X (LAA-X), a novel deepfake detection framework that is both robust to high-quality forgeries and capable of generalizing to unseen manipulations. Existing approaches typically rely on binary classifiers coupled with implicit attention mechanisms, which often fail to generalize beyond known manipulations. In contrast, LAA-X introduces an explicit attention strategy based on a multi-task learning framework combined with blending-based data synthesis. Auxiliary tasks are designed to guide the model toward localized, artifact-prone (i.e., vulnerable) regions. The proposed framework is compatible with both CNN and transformer backbones, resulting in two different versions, namely, LAA-Net and LAA-Former, respectively. Despite being trained only on real and pseudo-fake samples, LAA-X competes with state-of-the-art methods across multiple benchmarks. Code and pre-trained weights for LAA-Net\footnote{https://github.com/10Ring/LAA-Net} and LAA-Former\footnote{https://github.com/10Ring/LAA-Former} are publicly available.