PuriShield: Robust Defense against Unauthorized Diffusion Customization via Structured Protective Perturbations

Latent diffusion models have raised severe security concerns regarding unauthorized customization. Existing anti-customization defenses protect images by injecting subtle protective perturbations, yet such unstructured perturbations suffer from poor robustness against Diffusion-based Purification (DP). To tackle this limitation, this paper proposes $\text{PuriShield}$, a novel anti-customization method that trains a Robust Protective Perturbation Generator (RPPG) to adaptively produce structured protective perturbations. Specifically, $\text{PuriShield}$ incorporates three core designs: pattern density-guided generation to yield structured perturbations, latent distribution contrastive loss to refine protective perturbations, and embedded dual-head modulation to enable high-quality perturbation synthesis. Extensive experimental results demonstrate the advantages of $\text{PuriShield}$: ① Excellent effectiveness. It effectively defends against 5 unauthorized customization methods prior to purification. ② Strong robustness. Across 13 purification methods, it attains optimal robustness and significantly surpasses baselines against UDAP, a DP approach tailored to counter anti-customization defenses. ③ Great generalizability. It performs well in cross-task and cross-domain scenarios. ④ High efficiency. Training the RPPG takes only 31.6 minutes, with a mere 5.8 ms inference latency.