Multi-Feature Fusion Approach for Generative AI Images Detection

TL;DR

This paper proposes a multi-feature fusion framework combining statistical, semantic, and texture cues to improve the robustness and accuracy of detecting AI-generated images across diverse models.

Contribution

It introduces a systematic multi-feature fusion approach that outperforms existing single-feature detectors in identifying synthetic images from various generative models.

Findings

Fusion of MSCN, CLIP, and MLBP features improves detection accuracy.

The combined approach is more robust across different generative models.

Performance surpasses state-of-the-art methods on multiple benchmarks.

Abstract

The rapid evolution of Generative AI (GenAI) models has led to synthetic images of unprecedented realism, challenging traditional methods for distinguishing them from natural photographs. While existing detectors often rely on single-feature spaces, such as statistical regularities, semantic embeddings, or texture patterns, these approaches tend to lack robustness when confronted with diverse and evolving generative models. In this work, we investigate and systematically evaluate a multi-feature fusion framework that combines complementary cues from three distinct spaces: (1) Mean Subtracted Contrast Normalized (MSCN) features capturing low-level statistical deviations; (2) CLIP embeddings encoding high-level semantic coherence; and (3) Multi-scale Local Binary Patterns (MLBP) characterizing mid-level texture anomalies. Through extensive experiments on four benchmark datasets covering a wide range of generative models, we show that individual feature spaces exhibit significant performance variability across different generators. Crucially, the fusion of all three representations yields superior and more consistent performance, particularly in a challenging mixed-model scenario. Compared to state-of-the-art methods, the proposed framework yields consistently improved performance across all evaluated datasets. Overall, this work highlights the importance of hybrid representations for robust GenAI image detection and provides a principled framework for integrating complementary visual cues.