Which Face and Whose Identity? Solving the Dual Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios

TL;DR

This paper introduces DAWF, a novel multi-face watermarking framework that effectively localizes and traces deepfakes in complex multi-person scenarios, addressing limitations of existing single-face focused methods.

Contribution

The paper presents a new multi-face encoder-decoder architecture with regional supervision loss for improved deepfake localization and source tracing in multi-person environments.

Findings

DAWF achieves high accuracy in deepfake localization in multi-face scenes.

It effectively traces the source of deepfakes with embedded identity payloads.

Experimental results outperform existing methods in complex scenarios.

Abstract

Unlike single-face forgeries, deepfakes in complex multi-person interaction scenarios (such as group photos and multi-person meetings) more closely reflect real-world threats. Although existing proactive forensics solutions demonstrate good performance, they heavily rely on a "single-face" setting, making it difficult to effectively address the problems of deepfake localization and source tracing in complex multi-person environments. To address this challenge, we propose the Deep Attributable Watermarking Framework (DAWF). This framework adopts a novel multi-face encoder-decoder architecture that bypasses the cumbersome offline pre-processing steps of traditional forensics, facilitating efficient in-network parallel watermark embedding and cross-face collaborative processing. Crucially, we propose a selective regional supervision loss. This innovative mechanism guides the decoder to focus exclusively on the facial regions tampered with by deepfakes. Leveraging this mechanism alongside the embedded identity payloads, DAWF realizes the "which + who" goal, answering the dual questions of which facial region was forged and who was forged. Extensive experiments on challenging multi-face datasets show that DAWF achieves excellent deepfake localization and traceability in complex multi-person scenes.