FedForgery: Generalized Face Forgery Detection with Residual Federated Learning

TL;DR

FedForgery introduces a federated learning approach with residual feature learning to enhance face forgery detection while preserving privacy across decentralized devices, effectively handling diverse and unknown artifact types.

Contribution

The paper presents a novel federated learning framework with residual autoencoders for generalized face forgery detection, addressing privacy and distribution challenges.

Findings

Outperforms existing methods on public datasets

Effectively detects diverse and unknown forgery artifacts

Enhances generalization through federated training

Abstract

With the continuous development of deep learning in the field of image generation models, a large number of vivid forged faces have been generated and spread on the Internet. These high-authenticity artifacts could grow into a threat to society security. Existing face forgery detection methods directly utilize the obtained public shared or centralized data for training but ignore the personal privacy and security issues when personal data couldn't be centralizedly shared in real-world scenarios. Additionally, different distributions caused by diverse artifact types would further bring adverse influences on the forgery detection task. To solve the mentioned problems, the paper proposes a novel generalized residual Federated learning for face Forgery detection (FedForgery). The designed variational autoencoder aims to learn robust discriminative residual feature maps to detect forgery faces (with diverse or even unknown artifact types). Furthermore, the general federated learning strategy is introduced to construct distributed detection model trained collaboratively with multiple local decentralized devices, which could further boost the representation generalization. Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery. The designed novel generalized face forgery detection protocols and source code would be publicly available.