Safety
Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models
arXiv:2610.16835v1 Announce Type: cross Abstract: Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection ef
arXiv:2610.16835v1 Announce Type: cross Abstract: Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection effectiveness, clean fidelity, compatibility, and tamper resistance. We incorporate long-horizon attack simulations to strengthen resistance to protection removal. Experiments with a single protection tool show improved resistance to re-alignment at a cost to clean fidelity, motivating further research toward practical model-side protection.
Related
- One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
- Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey
Source: arXiv cs.CV | 2026-10-14