Preprint
Aug 2026
SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense
This work proposes SRAP, which combines per-channel truncated SVD refinement with an identity-importance mask at every optimization step, and demonstrates that SRAP substantially improves protected-image fidelity across all reported metrics while maintaining competitive identity-disruption performance.
S. Cho, Kwanghyun Ko, Myungjoo Kang
· 0 citations