FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
This addresses the problem of limited generalization in DeepFake detection for security applications, but it is incremental as it builds on existing pseudo-fake generation methods by adding frequency blending.
The paper tackled the problem of improving DeepFake detection generalization by generating pseudo-fake faces, and the result was that FreqBlender enhanced detection effectiveness as a potential plug-and-play strategy.
Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces {\em FreqBlender}, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods.