Decentralized Attribution of Generative Models
Decentralized Attribution of Generative Models
复制标题
DOI：
--
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Changhoon Kim;Yi Ren;Yezhou Yang
中科院分区：
文献类型：
--
作者：
Changhoon Kim;Yi Ren;Yezhou Yang
人们越来越关注通过生成模型制造内容。本文探讨了分散属性的这种模式的可行性。给定从同一数据集学习的一组生成模型，当存在公共验证服务以正确识别生成内容的源模型时，可以实现属性。归因允许将机器生成的内容追溯到其源模型，从而促进知识产权保护和内容监管。现有的归因方法是不可扩展的模型的数量方面，缺乏理论上的界限归因。本文研究了分散归因，其中可证明的归因性可以通过仅要求每个模型与真实数据区分开来来实现。我们的主要贡献是推导出分散属性的充分条件，并根据这些条件设计密钥。具体来说，我们证明了当密钥（1）彼此正交，以及（2）属于由数据分布确定的子空间时，可以实现分散的属性。该结果在MNIST和CelebA上得到验证。最后，我们使用这些数据集来检查生成质量和对抗性后处理的鲁棒可归因性之间的权衡。
There have been growing concerns regarding the fabrication of contents through generative models. This paper investigates the feasibility of decentralized attribution of such models. Given a set of generative models learned from the same dataset, attributability is achieved when a public verification service exists to correctly identify the source models for generated content. Attribution allows tracing of machine-generated content back to its source model, thus facilitating IP-protection and content regulation. Existing attribution methods are non-scalable with respect to the number of models and lack theoretical bounds on attributability. This paper studies decentralized attribution, where provable attributability can be achieved by only requiring each model to be distinguishable from the authentic data. Our major contributions are the derivation of the sufficient conditions for decentralized attribution and the design of keys following these conditions. Specifically, we show that decentralized attribution can be achieved when keys are (1) orthogonal to each other, and (2) belonging to a subspace determined by the data distribution. This result is validated on MNIST and CelebA. Lastly, we use these datasets to examine the trade-off between generation quality and robust attributability against adversarial post-processes.