Phase4DFD: Multi-Domain Phase-Aware Attention for Deepfake Detection

TL;DR

Phase4DFD introduces a phase-aware frequency domain framework for deepfake detection, leveraging phase magnitude interactions and attention mechanisms to improve accuracy over existing methods.

Contribution

The paper presents a novel phase-aware attention mechanism that explicitly models phase information in frequency domain deepfake detection, enhancing detection performance.

Findings

Outperforms state-of-the-art detectors on CIFAKE and DFFD datasets.

Explicit phase modeling provides complementary information beyond magnitude-only methods.

Maintains low computational overhead while improving detection accuracy.

Abstract

Recent deepfake detection methods have increasingly explored frequency domain representations to reveal manipulation artifacts that are difficult to detect in the spatial domain. However, most existing approaches rely primarily on spectral magnitude, implicitly under exploring the role of phase information. In this work, we propose Phase4DFD, a phase aware frequency domain deepfake detection framework that explicitly models phase magnitude interactions via a learnable attention mechanism. Our approach augments standard RGB input with Fast Fourier Transform (FFT) magnitude and local binary pattern (LBP) representations to expose subtle synthesis artifacts that remain indistinguishable under spatial analysis alone. Crucially, we introduce an input level phase aware attention module that uses phase discontinuities commonly introduced by synthetic generation to guide the model toward frequency patterns that are most indicative of manipulation before backbone feature extraction. The attended multi domain representation is processed by an efficient BNext M backbone, with optional channel spatial attention applied for semantic feature refinement. Extensive experiments on the CIFAKE and DFFD datasets demonstrate that our proposed model Phase4DFD outperforms state of the art spatial and frequency-based detectors while maintaining low computational overhead. Comprehensive ablation studies further confirm that explicit phase modeling provides complementary and non-redundant information beyond magnitude-only frequency representations.