ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation

TL;DR

ID-Eraser is a proactive face protection method that disrupts identity recognition in face swapping models by perturbing identity embeddings, producing realistic images while preventing malicious swaps.

Contribution

It introduces a feature-space defense that effectively neutralizes face swapping attacks by perturbing identity embeddings and reconstructing natural-looking protected images.

Findings

Substantially reduces identity recognition accuracy in face swapping systems.

Achieves lowest Top-1 accuracy of 0.30 and high visual quality metrics.

Demonstrates robustness across datasets, distortions, and commercial APIs.

Abstract

Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are ineffective against contemporary swapping models that extract robust high-level identity embeddings. We propose ID-Eraser, a feature-space proactive defense that removes identifiable facial information to prevent malicious face swapping. By injecting learnable perturbations into identity embeddings and reconstructing natural-looking protection images through a Face Revive Generator (FRG), ID-Eraser produces visually realistic results for humans while rendering the protected identities unusable for Deepfake models. Experiments show that ID-Eraser substantially disrupts identity recognition across diverse face recognition and swapping systems under strict black-box settings, achieving the lowest Top-1 accuracy (0.30) with the best FID (1.64) and LPIPS (0.020). Compared with swaps generated from clean inputs, the identity similarity of protected swaps drops sharply to an average of 0.504 across five representative face swapping models. ID-Eraser further demonstrates strong cross-dataset generalization, robustness to common distortions, and practical effectiveness on commercial APIs, reducing Tencent API similarity from 0.76 to 0.36.