Handcrafted Feature Fusion for Reliable Detection of AI-Generated Images

TL;DR

This paper systematically evaluates handcrafted features combined with ensemble classifiers for detecting AI-generated images, demonstrating high accuracy and emphasizing interpretability and efficiency over deep learning methods.

Contribution

It provides a comprehensive benchmark of handcrafted descriptors and classifiers, showing that feature fusion with LightGBM achieves state-of-the-art detection performance.

Findings

LightGBM outperforms other classifiers in detection accuracy.

Combining diverse handcrafted features improves performance monotonically.

The approach offers high interpretability and computational efficiency.

Abstract

The rapid progress of generative models has enabled the creation of highly realistic synthetic images, raising concerns about authenticity and trust in digital media. Detecting such fake content reliably is an urgent challenge. While deep learning approaches dominate current literature, handcrafted features remain attractive for their interpretability, efficiency, and generalizability. In this paper, we conduct a systematic evaluation of handcrafted descriptors, including raw pixels, color histograms, Discrete Cosine Transform (DCT), Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), Gray-Level Co-occurrence Matrix (GLCM), and wavelet features, on the CIFAKE dataset of real versus synthetic images. Using 50,000 training and 10,000 test samples, we benchmark seven classifiers ranging from Logistic Regression to advanced gradient-boosted ensembles (LightGBM, XGBoost, CatBoost). Results demonstrate that LightGBM consistently outperforms alternatives, achieving PR-AUC 0.9879, ROC-AUC 0.9878, F1 0.9447, and a Brier score of 0.0414 with mixed features, representing strong gains in calibration and discrimination over simpler descriptors. Across three configurations (baseline, advanced, mixed), performance improves monotonically, confirming that combining diverse handcrafted features yields substantial benefit. These findings highlight the continued relevance of carefully engineered features and ensemble learning for detecting synthetic images, particularly in contexts where interpretability and computational efficiency are critical.