Trustless Audits without Revealing Data or Models

arXiv:2404.04500v1 Announce Type: cross
Abstract: There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholder wishing to know whether their copyrighted works have been used during training must convince the model provider to allow a third party to audit the model and data. Finding a mutually agreeable third party is difficult, and the associated costs often make this approach impractical.
In this work, …

abstract algorithmic transparency arxiv business conflict cs.ai cs.cr cs.cy cs.lg data example hide incentives provider secrets trade training transparency type