Deepfake Face Traceability with Disentangling Reversing Network

TL;DR

This paper introduces a disentangling reversing network that can trace the original face from a deepfake, enabling source identification and advancing forensic capabilities beyond simple deepfake detection.

Contribution

It proposes a novel network that reconstructs original faces from deepfakes, addressing the need for deepfake source traceability in forensic applications.

Findings

Successfully reconstructs original faces from deepfakes

Enables source tracing for deepfake forensic analysis

Improves understanding of deepfake face features

Abstract

Deepfake face not only violates the privacy of personal identity, but also confuses the public and causes huge social harm. The current deepfake detection only stays at the level of distinguishing true and false, and cannot trace the original genuine face corresponding to the fake face, that is, it does not have the ability to trace the source of evidence. The deepfake countermeasure technology for judicial forensics urgently calls for deepfake traceability. This paper pioneers an interesting question about face deepfake, active forensics that "know it and how it happened". Given that deepfake faces do not completely discard the features of original faces, especially facial expressions and poses, we argue that original faces can be approximately speculated from their deepfake counterparts. Correspondingly, we design a disentangling reversing network that decouples latent space features of deepfake faces under the supervision of fake-original face pair samples to infer original faces in reverse.