Fooling State-of-the-Art Deepfake Detection with High-Quality Deepfakes

TL;DR

This paper demonstrates that high-quality deepfakes can significantly undermine state-of-the-art detectors, highlighting the need for including such samples in training datasets to improve robustness.

Contribution

The authors introduce a novel autoencoder and face blending technique to generate high-quality deepfakes that challenge existing detectors and show the importance of high-quality fake data for training.

Findings

High-quality deepfakes reduce detector performance

Fine-tuning with high-quality fakes improves detection clues

Research datasets alone are insufficient for robust detection

Abstract

Due to the rising threat of deepfakes to security and privacy, it is most important to develop robust and reliable detectors. In this paper, we examine the need for high-quality samples in the training datasets of such detectors. Accordingly, we show that deepfake detectors proven to generalize well on multiple research datasets still struggle in real-world scenarios with well-crafted fakes. First, we propose a novel autoencoder for face swapping alongside an advanced face blending technique, which we utilize to generate 90 high-quality deepfakes. Second, we feed those fakes to a state-of-the-art detector, causing its performance to decrease drastically. Moreover, we fine-tune the detector on our fakes and demonstrate that they contain useful clues for the detection of manipulations. Overall, our results provide insights into the generalization of deepfake detectors and suggest that their training datasets should be complemented by high-quality fakes since training on mere research data is insufficient.