检测模型是否偷偷用了你的生成数据训练，准确率超99%
Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
- 基于泛化误差边界原理，比对训练数据分布距离
- 在4个文生图模型上验证，准确率超99%
- 适合模型版权保护者和生成模型开发者
高质量开源文本到图像模型显著降低了获取逼真图像的门槛，但也面临被滥用的风险。例如，当缺乏真实数据资源时，攻击者可能使用这些生成模型合成的数据来训练特定任务模型，而未经许可。保护生成模型对所有者至关重要。本文提出首个解决该问题的方法——训练数据溯源验证（TrainProVe）。其原理基于泛化误差界理论：若两个模型任务相同，其训练数据分布距离越近，泛化能力越接近。我们在四个文生图模型（Stable Diffusion v1.4、latent consistency model、PixArt-α、Stable Cascade）上验证了方法有效性，结果表明TrainProVe在判断可疑模型训练数据来源时，验证准确率超过99%，显著优于此前所有方法。代码已公开于 https://github.com/xieyc99/TrainProVe。
原文摘要 · Abstract (English)
High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative models to train models for specific tasks without permission, when lacking real data resources especially. Protecting these generative models is crucial for the well-being of their owners. In this work, we propose the first method to this important yet unresolved issue, called Training data Provenance Verification (TrainProVe). The rationale behind TrainProVe is grounded in the principle of generalization error bound, which suggests that, for two models with the same task, if the distance between their training data distributions is smaller, their generalization ability will be closer. We validate the efficacy of TrainProVe across four text-to-image models (Stable Diffusion v1.4, latent consistency model, PixArt-$α$, and Stable Cascade). The results show that TrainProVe achieves a verification accuracy of over 99\% in determining the provenance of suspicious model training data, surpassing all previous methods. Code is available at https://github.com/xieyc99/TrainProVe.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。