Security and Privacy Considerations for Machine Learning Models Deployed in the Government and Public Sector (white paper)

TL;DR

This white paper discusses security and privacy challenges in deploying machine learning models in government and public sectors, emphasizing the need for protective measures, transparency, and accountability.

Contribution

It provides an overview of potential attacks, defense strategies, and offers recommendations to enhance security and privacy in government ML deployments.

Findings

Identification of key security threats and privacy risks.

Summary of attack and defense scenarios.

Guidelines for improving ML deployment security.

Abstract

As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use cases require special considerations for implementation given the significance of the services they provide. Not only will these applications be deployed in a potentially hostile environment that necessitates protective mechanisms, but they are also subject to government transparency and accountability initiatives which further complicates such protections. In this paper, we describe how the inevitable interactions between a user of unknown trustworthiness and the machine learning models, deployed in governments and public sectors, can jeopardize the system in two major ways: by compromising the integrity or by violating the privacy. We then briefly overview the possible attacks and defense scenarios, and finally, propose recommendations and guidelines that once considered can enhance the security and privacy of the provided services.