LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals

arXiv:2608.20882v1 Announce Type: new Abstract: Modern generators faithfully model macroscopic semantics, producing synthetic images that appear highly realistic. Consequently, decisive forensic cues reside in subtle non-semantic visual discrepancies. To reveal these cues, we revisit AIGI detection from a geometric perspective and identify an architecture-agnostic signature. Specifically, modern generators exhibit low-rank collapse (extit{i.e.}, rank degeneracy) in the semantic-residual orthogonal subspace while largely preserving the dominant semantic direction. This structural flattening consistently emerges during the final decoding stage, forming a shared bottleneck across diverse generator architectures. Motivated by this signature, we propose extbf{LoRC}, a framework that decouples semantic dominance to capture the collapsed residual geometry induced by the generative decoding bottleneck. Our method improves accuracy by an average of 7.0% across multiple benchmarks and achieves 97.0% accuracy on 39 unseen generators. These results demonstrate strong cross-model generalization and robustness, making LoRC a reliable approach for AIGI detection in complex real-world environments.

Related

• Quality-Aware Calibration for AI-Generated Image Detection in the Wild
• Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
• Abductive Corroboration of Probabilistic AI Models for Forensic Synthetic Media Detection

Source: arXiv cs.CV | 2026-08-24