MLCRLGJul 1, 2016

Deep Learning with Differential Privacy

arXiv:1607.00133v27807 citations
AI Analysis

This addresses privacy concerns for machine learning practitioners handling sensitive data, representing a novel method rather than an incremental improvement.

The paper tackles the problem of training deep neural networks without exposing sensitive information in training datasets by developing new algorithmic techniques within the differential privacy framework, achieving training under a modest privacy budget with manageable costs in software complexity, training efficiency, and model quality.

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy. Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality.

Code Implementations26 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes