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

2026-08-21

AI Summary

本文通过识别生成图像在语义残差正交子空间中的低秩塌陷特征，提出LoRC框架以提高AI生成图像检测的准确性。

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 (\textit{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 \textbf{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.

Problem

• AI-Generated Images
• Low-Rank Collapse
• Semantic Residuals

Innovation

• low-rank collapse
• semantic residuals
• generative decoding bottleneck
• cross-model generalization