DFREC: DeepFake Identity Recovery Based on Identity-aware Masked Autoencoder

TL;DR

DFREC is a novel deepfake recovery method that reconstructs source and target faces from deepfake images, enhancing identity traceability and forensic investigation with high fidelity.

Contribution

It introduces a new deepfake recovery scheme with an identity segmentation and reconstruction framework, improving over existing detection-focused methods.

Findings

Superior recovery performance on multiple datasets

Able to recover both source and target faces with high fidelity

Outperforms state-of-the-art deepfake recovery algorithms

Abstract

Recent advances in deepfake forensics have primarily focused on improving the classification accuracy and generalization performance. Despite enormous progress in detection accuracy across a wide variety of forgery algorithms, existing algorithms lack intuitive interpretability and identity traceability to help with forensic investigation. In this paper, we introduce a novel DeepFake Identity Recovery scheme (DFREC) to fill this gap. DFREC aims to recover the pair of source and target faces from a deepfake image to facilitate deepfake identity tracing and reduce the risk of deepfake attack. It comprises three key components: an Identity Segmentation Module (ISM), a Source Identity Reconstruction Module (SIRM), and a Target Identity Reconstruction Module (TIRM). The ISM segments the input face into distinct source and target face information, and the SIRM reconstructs the source face and extracts latent target identity features with the segmented source information. The background context and latent target identity features are synergetically fused by a Masked Autoencoder in the TIRM to reconstruct the target face. We evaluate DFREC on six different high-fidelity face-swapping attacks on FaceForensics++, CelebaMegaFS and FFHQ-E4S datasets, which demonstrate its superior recovery performance over state-of-the-art deepfake recovery algorithms. In addition, DFREC is the only scheme that can recover both pristine source and target faces directly from the forgery image with high fadelity.