Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar

Abstract:

Some machine learning applications involve training data that is sensitive, such
as the medical histories of patients in a clinical trial. A model may
inadvertently and implicitly store some of its training data; careful analysis
of the model may therefore reveal sensitive information.

To address this problem, we demonstrate a generally applicable approach to
providing strong privacy guarantees for training data: Private Aggregation of Teacher Ensembles (PATE). The approach combines, in
a black-box fashion, multiple models trained with disjoint datasets, such as
records from different subsets of users. Because they rely directly on sensitive
data, these models are not published, but instead used as ''teachers'' for a ''student'' model.
The student learns to predict an output chosen by noisy voting
among all of the teachers, and cannot directly access an individual teacher or
the underlying data or parameters. The student's privacy properties can be
understood both intuitively (since no single teacher and thus no single dataset
dictates the student's training) and formally, in terms of differential privacy.
These properties hold even if an adversary can not only query the student but
also inspect its internal workings.

Compared with previous work, the approach imposes only weak assumptions on how
teachers are trained: it applies to any model, including non-convex models like
DNNs. We achieve state-of-the-art privacy/utility trade-offs on MNIST and SVHN
thanks to an improved privacy analysis and semi-supervised learning.

TL;DR: Semi-supervised learning of a privacy-preserving student model with GANs by knowledge transfer from an ensemble of teachers trained on partitions of private data.

Conflicts: google.com, openai.com, psu.edu

Community Implementations: [ 6 code implementations](https://www.catalyzex.com/paper/arxiv:1610.05755/code)