Search papers, labs, and topics across Lattice.
This paper introduces GLID, a novel approach to enhance face-forgery detection by addressing the limitations of existing fine-tuned models that struggle with unseen generator families. By treating image patch tokens as samples from a manifold and estimating their local intrinsic dimension (LID) using a frozen vision transformer, GLID provides a training-free geometric signal that significantly improves detection performance. The method achieves a mean AUC of 0.805 on a comprehensive cross-generator benchmark, outperforming state-of-the-art baselines while maintaining stability across various axes of evaluation.
GLID achieves a remarkable 0.805 mean AUC on a 16-axis benchmark, outperforming traditional fine-tuned detectors by leveraging geometric signals instead of additional training data.
Fine-tuned foundation-model detectors dominate face-forgery benchmarks, yet they stay blind to generator families absent from training. We present GLID, a detector that repairs this blind spot with geometry instead of data. GLID treats the patch tokens of a single image as a sample from a manifold and estimates their local intrinsic dimension (LID) at several depths of a frozen vision transformer. This 12-dimensional, training-free signal enters a fine-tuned detector through a confidence gate whose strength is calibrated purely in-distribution. On a 16-axis cross-generator benchmark, GLID reaches 0.805 mean AUC, first among retrained state-of-the-art baselines and never significantly behind the strongest of them on any axis. It lifts the generation axes by +0.084 AUC while moving reenactment by only -0.005. Two empirical laws explain the design. First, forged faces bend the token manifold at family-specific depths: GAN artifacts peak at the last layer, diffusion artifacts peak mid-network, and the pattern survives four backbones, three dimension estimators, and non-face imagery. Second, fine-tuning absorbs auxiliary gains exactly where training data covers: injecting 1% target-family images erases a +0.100 gain, so geometric signals matter precisely where data is unavailable. The deterministic signal also cuts the cross-seed spread of accuracy 5.5x. Code, preregistered analysis gates, and per-image scores accompany the paper.
