Cross-Domain Local Characteristic Enhanced Deepfake Video Detection

TL;DR

This paper introduces a novel deepfake detection method that leverages cross-domain local features from space, frequency, and time domains, focusing on critical facial regions to improve generalization across datasets.

Contribution

The proposed Cross-Domain Local Forensics (XDLF) framework uniquely combines multi-domain features and facial region analysis for more robust deepfake detection.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Demonstrates strong cross-dataset generalization

Ablation studies highlight the importance of cross-domain local features

Abstract

As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns. Many detectors cannot achieve accurate results when detecting unseen manipulations despite excellent performance on known forgeries. In this paper, we are motivated by the observation that the discrepancies between real and fake videos are extremely subtle and localized, and inconsistencies or irregularities can exist in some critical facial regions across various information domains. To this end, we propose a novel pipeline, Cross-Domain Local Forensics (XDLF), for more general deepfake video detection. In the proposed pipeline, a specialized framework is presented to simultaneously exploit local forgery patterns from space, frequency, and time domains, thus learning cross-domain features to detect forgeries. Moreover, the framework leverages four high-level forgery-sensitive local regions of a human face to guide the model to enhance subtle artifacts and localize potential anomalies. Extensive experiments on several benchmark datasets demonstrate the impressive performance of our method, and we achieve superiority over several state-of-the-art methods on cross-dataset generalization. We also examined the factors that contribute to its performance through ablations, which suggests that exploiting cross-domain local characteristics is a noteworthy direction for developing more general deepfake detectors.