RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services
RAPID embeds defensive perturbations in a T2I model's shared VAE decoder to block unauthorized black-box distillation in real time.
The paper defends text-to-image services against model theft via black-box output-based distillation, where adversaries collect prompt-image pairs to train substitute models. RAPID integrates defensive perturbations into the shared VAE decoder using self-referenced latent maximization plus reconstruction-guided color regularization, avoiding costly sample-wise online optimization. Across four T2I models and four datasets versus five baselines, it consistently degrades substitute-model generation quality while preserving visual fidelity.
- Defends T2I services against unauthorized distillation without online per-sample optimization
- Self-referenced latent maximization improves transfer to a shared defensive decoder
- Validated on four T2I models and four datasets against five baselines
From the original article
1 min read at arxiv.orgDiffusion-based text-to-image (T2I) models are increasingly used for visual content creation, making their generation capability a valuable intellectual property asset. However, this capability is vulnerable to black-box output-based distillation, where an adversary queries the service, collects prompt-image pairs, and trains an unauthorized substitute model that mimics its generation behavior.
By Zihan Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.