DeepFeatureX Net: Deep Features eXtractors based Network for discriminating synthetic from real images

TL;DR

This paper introduces DeepFeatureX Net, a novel neural network architecture that effectively discriminates between real and AI-generated images, demonstrating strong generalization and robustness against compression artifacts.

Contribution

It proposes a new multi-block feature extraction approach that improves generalization in deepfake detection across unseen architectures.

Findings

Outperforms state-of-the-art methods in generalization tests

Maintains robustness against JPEG compression

Effective in distinguishing real from synthetic images

Abstract

Deepfakes, synthetic images generated by deep learning algorithms, represent one of the biggest challenges in the field of Digital Forensics. The scientific community is working to develop approaches that can discriminate the origin of digital images (real or AI-generated). However, these methodologies face the challenge of generalization, that is, the ability to discern the nature of an image even if it is generated by an architecture not seen during training. This usually leads to a drop in performance. In this context, we propose a novel approach based on three blocks called Base Models, each of which is responsible for extracting the discriminative features of a specific image class (Diffusion Model-generated, GAN-generated, or real) as it is trained by exploiting deliberately unbalanced datasets. The features extracted from each block are then concatenated and processed to discriminate the origin of the input image. Experimental results showed that this approach not only demonstrates good robust capabilities to JPEG compression but also outperforms state-of-the-art methods in several generalization tests. Code, models and dataset are available at https://github.com/opontorno/block-based_deepfake-detection.