Learning Pairwise Interaction for Generalizable DeepFake Detection

TL;DR

This paper introduces MCX-API, a novel deepfake detection method that leverages pairwise learning and multi-color space features, demonstrating superior generalization across unseen DeepFake schemes and datasets.

Contribution

The paper proposes MCX-API, a new approach combining pairwise learning and multi-channel color representations to improve deepfake detection generalization.

Findings

Achieves 98.48% BOSC accuracy on FF++ dataset

Attains 90.87% BOSC accuracy on CelebDF dataset

Outperforms state-of-the-art detectors in open-set scenarios

Abstract

A fast-paced development of DeepFake generation techniques challenge the detection schemes designed for known type DeepFakes. A reliable Deepfake detection approach must be agnostic to generation types, which can present diverse quality and appearance. Limited generalizability across different generation schemes will restrict the wide-scale deployment of detectors if they fail to handle unseen attacks in an open set scenario. We propose a new approach, Multi-Channel Xception Attention Pairwise Interaction (MCX-API), that exploits the power of pairwise learning and complementary information from different color space representations in a fine-grained manner. We first validate our idea on a publicly available dataset in a intra-class setting (closed set) with four different Deepfake schemes. Further, we report all the results using balanced-open-set-classification (BOSC) accuracy in an inter-class setting (open-set) using three public datasets. Our experiments indicate that our proposed method can generalize better than the state-of-the-art Deepfakes detectors. We obtain 98.48% BOSC accuracy on the FF++ dataset and 90.87% BOSC accuracy on the CelebDF dataset suggesting a promising direction for generalization of DeepFake detection. We further utilize t-SNE and attention maps to interpret and visualize the decision-making process of our proposed network. https://github.com/xuyingzhongguo/MCX-API