Information Flow Control in Machine Learning through Modular Model Architecture

arXiv:2306.03235v2 Announce Type: replace-cross
Abstract: In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is a major obstacle in training models on sensitive data when access control only allows individual users to access a subset of data. To enable secure machine learning for access-controlled data, we propose the notion of information flow control for machine learning, and …

access access control architecture arxiv can control cs.cr cs.lg data flow information machine machine learning major modular sensitive sensitive data today training training data