ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces

TL;DR

This paper introduces a series of forest-based models called ForensicsForest Family for detecting GAN-generated faces, leveraging multi-scale features and hierarchical cascades to improve detection accuracy over CNN-based methods.

Contribution

The paper proposes a novel forest-based approach with three variants, integrating multi-scale features and hierarchical cascades, offering an effective alternative to CNNs for GAN face detection.

Findings

ForensicsForest achieves high detection accuracy on benchmark datasets.

Hybrid ForensicsForest improves performance by combining CNN and forest features.

Divide-and-Conquer ForensicsForest reduces training memory costs significantly.

Abstract

The prominent progress in generative models has significantly improved the reality of generated faces, bringing serious concerns to society. Since recent GAN-generated faces are in high realism, the forgery traces have become more imperceptible, increasing the forensics challenge. To combat GAN-generated faces, many countermeasures based on Convolutional Neural Networks (CNNs) have been spawned due to their strong learning ability. In this paper, we rethink this problem and explore a new approach based on forest models instead of CNNs. Specifically, we describe a simple and effective forest-based method set called {\em ForensicsForest Family} to detect GAN-generate faces. The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively. ForenscisForest is a newly proposed Multi-scale Hierarchical Cascade Forest, which takes semantic, frequency and biology features as input, hierarchically cascades different levels of features for authenticity prediction, and then employs a multi-scale ensemble scheme that can comprehensively consider different levels of information to improve the performance further. Based on ForensicsForest, we develop Hybrid ForensicsForest, an extended version that integrates the CNN layers into models, to further refine the effectiveness of augmented features. Moreover, to reduce the memory cost in training, we propose Divide-and-Conquer ForensicsForest, which can construct a forest model using only a portion of training samplings. In the training stage, we train several candidate forest models using the subsets of training samples. Then a ForensicsForest is assembled by picking the suitable components from these candidate forest models...