Detecting AI-Generated Images via Contextual Anomaly Estimation in Masked AutoEncoders

TL;DR

This paper introduces CINEMAE, a novel detection method that combines patch-level anomaly signals and global semantic features from Masked AutoEncoders to improve the robustness of AI-generated image detection.

Contribution

CINEMAE leverages both reconstruction-based anomaly detection and semantic feature extraction from MAE for more reliable AI-generated image detection.

Findings

Achieves 96.63% accuracy on GenImage

Maintains over 93% accuracy under JPEG compression

Outperforms existing detectors in robustness

Abstract

Context-based detection methods such as DetectGPT achieve strong generalization in identifying AI-generated text by evaluating content compatibility with a model's learned distribution. In contrast, existing image detectors rely on discriminative features from pretrained backbones such as CLIP, which implicitly capture generator-specific artifacts. However, as modern generative models rapidly advance in visual fidelity, the artifacts these detectors depend on are becoming increasingly subtle or absent, undermining their reliability. Masked AutoEncoders (MAE) are inherently trained to reconstruct masked patches from visible context, naturally modeling patch-level contextual plausibility akin to conditional probability estimation, while also serving as a powerful semantic feature extractor through its encoder. We propose CINEMAE, a novel architecture that exploits both capabilities of MAE for AI-generated image detection: we derive per-patch anomaly signals from the reconstruction mechanism and extract global semantic features from the encoder, fusing both context-based and feature-based cues for robust detection. CINEMAE achieves highly competitive mean accuracies of 96.63\% on GenImage and 93.96\% on AIGCDetectBenchmark, maintaining over 93\% accuracy even under JPEG compression at QF=50.