Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection

TL;DR

This paper introduces a novel face deepfake detection method using cross-branch orthogonality to improve generalization across diverse deepfake types, outperforming existing methods on multiple benchmarks.

Contribution

It proposes a feature orthogonality-based disentanglement strategy for better generalization in deepfake detection, addressing limitations of artifact-based methods.

Findings

Outperforms state-of-the-art by 5% on Celeb-DF

Achieves 7% improvement on DFDC in cross-dataset tests

Effective in detecting diverse and unseen deepfake types

Abstract

Remarkable advancements in generative AI technology have given rise to a spectrum of novel deepfake categories with unprecedented leaps in their realism, and deepfakes are increasingly becoming a nuisance to law enforcement authorities and the general public. In particular, we observe alarming levels of confusion, deception, and loss of faith regarding multimedia content within society caused by face deepfakes, and existing deepfake detectors are struggling to keep up with the pace of improvements in deepfake generation. This is primarily due to their reliance on specific forgery artifacts, which limits their ability to generalise and detect novel deepfake types. To combat the spread of malicious face deepfakes, this paper proposes a new strategy that leverages coarse-to-fine spatial information, semantic information, and their interactions while ensuring feature distinctiveness and reducing the redundancy of the modelled features. A novel feature orthogonality-based disentanglement strategy is introduced to ensure branch-level and cross-branch feature disentanglement, which allows us to integrate multiple feature vectors without adding complexity to the feature space or compromising generalisation. Comprehensive experiments on three public benchmarks: FaceForensics++, Celeb-DF, and the Deepfake Detection Challenge (DFDC) show that these design choices enable the proposed approach to outperform current state-of-the-art methods by 5% on the Celeb-DF dataset and 7% on the DFDC dataset in a cross-dataset evaluation setting.