Kavli Affiliate: Wei Gao | First 5 Authors: Kai Huang, Wei Gao, , , | Summary: Text-to-image diffusion models can be fine-tuned in custom domains to adapt to specific user preferences, but such unconstrained adaptability has also been utilized for illegal purposes, such as forging public figures’ portraits and duplicating copyrighted artworks. Most existing work […]
Continue.. FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing