Dual Attention Guided Defense Against Malicious Edits

Summary

Researchers propose DANP (Dual Attention-Guided Noise Perturbation), an immunization method that adds imperceptible perturbations to text-to-image diffusion models to resist malicious edits. DANP works across multiple timesteps, reducing cross-attention in text-relevant regions while increasing it in irrelevant ones, and maximizes the discrepancy between injected noise and predicted noise. The authors report state-of-the-art performance against malicious edits.