Robust Identity Perceptual Watermark Against Deepfake Face Swapping

TL;DR

This paper introduces a robust identity perceptual watermarking framework that proactively detects and traces Deepfake face swaps by embedding and recovering identity-based watermarks, achieving state-of-the-art performance in robustness and accuracy.

Contribution

It proposes a novel identity perceptual watermarking method with chaotic encryption for proactive Deepfake defense, improving detection accuracy, visual quality, and source tracing capabilities.

Findings

State-of-the-art detection accuracy against Deepfake face swapping

High robustness of watermarks across datasets and manipulations

Effective source tracing based on identity semantics

Abstract

Notwithstanding offering convenience and entertainment to society, Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models. Due to imperceptible artifacts in high-quality synthetic images, passive detection models against face swapping in recent years usually suffer performance damping regarding the generalizability issue in cross-domain scenarios. Therefore, several studies have been attempted to proactively protect the original images against malicious manipulations by inserting invisible signals in advance. However, existing proactive defense approaches demonstrate unsatisfactory results with respect to visual quality, detection accuracy, and source tracing ability. In this study, to fulfill the research gap, we propose a robust identity perceptual watermarking framework that concurrently performs detection and source tracing against Deepfake face swapping proactively. We innovatively assign identity semantics regarding the image contents to the watermarks and devise an unpredictable and nonreversible chaotic encryption system to ensure watermark confidentiality. The watermarks are robustly encoded and recovered by jointly training an encoder-decoder framework along with adversarial image manipulations. For a suspect image, falsification is accomplished by justifying the consistency between the content-matched identity perceptual watermark and the recovered robust watermark, without requiring the ground-truth. Moreover, source tracing can be accomplished based on the identity semantics that the recovered watermark carries. Extensive experiments demonstrate state-of-the-art detection and source tracing performance against Deepfake face swapping with promising watermark robustness for both cross-dataset and cross-manipulation settings.