This post is part of a series on privacy-preserving federated learning. The series is a collaboration between NIST and the UK government’s Responsible Technology Adoption Unit (RTA), previously known as the Centre for Data Ethics and Innovation. Learn more and read all the posts published to date at NIST’s Privacy Engineering Collaboration Space or RTA’s blog . The last two posts in our series covered techniques for input privacy in privacy-preserving federated learning in the context of horizontally and vertically partitioned data. To build a complete privacy-preserving federated learning ..read more

The last few months have brought even more opportunities for NIST to engage with our international partners to enhance cybersecurity. Here are some updates on our recent international engagement: Conversations have continued with our partners throughout the world on the recent release of the Cybersecurity Framework Version 2.0 . NIST international engagement continues through our support to the Department of State and the International Trade Administration (ITA) during numerous international dialogues. Most recently, NIST participated in interagency dialogues to share information on NIST ..read more

Can you recall the last time you opened a bank account? It’s likely you walked into a local bank branch and spoke to a representative who asked for your driver’s license and social security card to verify your identity. Now imagine you want to create a bank account online. The process is likely similar—type in your social security number, take a picture of your driver’s license, and submit both to the bank via their webpage. Seems straightforward, right? Identity verification is important—it protects us from identity theft and reduces the risk of fraud and unauthorized access for organizations ..read more

I joined NIST as the first full-time manager of the NICE Framework in October 2020, just one short month before NICE published the first revision NIST Special Publication 800-181, the NICE Workforce Framework for Cybersecurity (NICE Framework). That revision – far from finalizing work – was the starting point that led us to a complete refresh of the NICE Framework components, which includes: Revised Work Role Categories and Work Roles – including one new Work Role. Eleven new Competency Areas that extend the Framework’s cybersecurity knowledge and skills. Updated Task, Knowledge, and Skill ..read more

The problem The previous post in our series discussed techniques for providing input privacy in PPFL systems where data is horizontally partitioned. This blog will focus on techniques for providing input privacy when data is vertically partitioned . As described in our third post , vertical partitioning is where the training data is divided across parties such that each party holds different columns of the data. In contrast to horizontally partitioned data, training a model on vertically partitioned data is more challenging as it is generally not possible to train separate models on different ..read more

The U.S. Small Business Administration is celebrating National Small Business Week from April 28 - May 4, 2024. This week recognizes and celebrates the small business community’s significant contributions to the nation. Organizations across the country participate by hosting in-person and virtual events, recognizing small business leaders and change-makers, and highlighting resources that help the small business community more easily and efficiently start and scale their businesses. To add to the festivities, this NIST Cybersecurity Insights blog showcases the NIST Cybersecurity Framework 2.0 ..read more

We all need supplements sometimes. Whether it’s a little extra vitamin C during flu season or some vitamin D during the dark days of Winter. When used correctly, supplements help our body adjust to the changing conditions around us. Similarly, we are applying this same concept for the first time to our NIST SP 800-63B, Digital Identity Guidelines: Authentication and Lifecycle Management. Today, we published a supplement that provides interim guidance for agencies seeking to make use of ‘syncable authenticators’ ( for example, passkeys) in both enterprise-facing and public-facing use cases ..read more

In our second post we described attacks on models and the concepts of input privacy and output privacy . ln our last post , we described horizontal and vertical partitioning of data in privacy-preserving federated learning (PPFL) systems. In this post, we explore the problem of providing input privacy in PPFL systems for the horizontally-partitioned setting. Models, training, and aggregation To explore techniques for input privacy in PPFL, we first have to be more precise about the training process. In horizontally-partitioned federated learning, a common approach is to ask each participant to ..read more

Last November, I was pleased to chair the most recent meeting of the Interagency International Cybersecurity Standardization Working Group (IICSWG) – a group NIST created in 2016. Our charge, from the Cybersecurity Enhancement Act of 2014, was to build a coordination mechanism for government agencies to discuss international cybersecurity standardization issues, consistent with agencies’ responsibilities under OMB Circular A-119. Since then, IICSWG has grown as a forum to discuss cybersecurity and privacy standardization topics, examine the overall cybersecurity standardization landscape ..read more

This post is part of a series on privacy-preserving federated learning. The series is a collaboration between NIST and the UK government’s Responsible Technology Adoption Unit (RTA), previously known as the Centre for Data Ethics and Innovation. Learn more and read all the posts published to date at NIST’s Privacy Engineering Collaboration Space or RTA’s blog . Our first post in the series introduced the concept of federated learning and described how it’s different from traditional centralized learning - in federated learning, the data is distributed among participating organizations, and ..read more