Search papers, labs, and topics across Lattice.
The paper introduces ID-Eraser, a novel proactive defense against face swapping that operates in the feature space by perturbing identity embeddings. A Face Revive Generator (FRG) reconstructs natural-looking images from these perturbed embeddings, ensuring visual realism for humans. Experiments demonstrate ID-Eraser's effectiveness in disrupting identity recognition and face swapping across various systems, achieving state-of-the-art results in black-box settings and demonstrating robustness against common distortions and commercial APIs.
Stop deepfakes before they start: ID-Eraser makes faces unusable for swapping by injecting subtle, learnable perturbations directly into identity embeddings.
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.
