PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing

2026-07-20

AI Summary

This work addresses the critical threat posed by deepfakes—particularly face-swapping attacks—to identity authenticity and security, noting that existing defenses predominantly rely on post-hoc detection and lack proactive protection. To bridge this gap, the authors propose an active defense mechanism that imperceptibly embeds identity-specific markers into user images, steering face-swap generators toward producing outputs aligned with a decoy identity. This approach not only disrupts successful attacks but also enables post-attack traceability. It represents the first method to jointly safeguard both user identity and contextual information while integrating feature-level forensic traceability, thereby transcending conventional passive detection paradigms. Extensive experiments demonstrate its efficacy across multiple state-of-the-art face-swapping models, reducing the success rate of SimSwap attacks to 0.30% and achieving 97.97% accuracy in identifying generated forgeries.

Abstract

Deepfakes, especially face-swapping attacks, pose significant challenges to authenticity, security, and ethics across science, engineering, and society. While most existing detection/tracing approaches operate post hoc, proactive defenses that aim to intervene before deepfake generation remain limited in terms of real-world effectiveness. In this paper, we present PhantomSeal, the first proactive defense to simultaneously protect both the identity and the context of users' images from being used in face-swapping attacks, while supporting forensic tracing. We present a novel cloaking technique that embeds a selected identity as a stealthy identifier. This mechanism steers the deepfake generation process toward producing content that resembles the chosen cloak identity, thereby preventing successful face-swapping while enabling effective feature-based forensic analysis. The effectiveness and robustness of PhantomSeal is demonstrated in extensive experiments across different face-swapping architectures and models. For example, it reduces the attack success rate of SimSwap, an advanced deepfake model, to 0.30%, and correctly identifies 97.97% of manipulated content. Codes can be found at https://github.com/LiangqinRen/PhantomSeal

Problem

• Deepfakes
• face-swapping attacks
• proactive defense
• identity protection
• forensic tracing

Innovation

• proactive defense
• identity protection
• forensic tracing
• deepfakes
• cloaking technique