IBM Research releases differential privacy library that works with machine learning

ibm-research-releases-differential-privacy-library-that-works-with-machine-learning

The open-source repository is unique in that most tasks can be run with only a single line of code, according to the company.

Padlock on computer motherboard cpu socket chip. Internet data privacy information security concept. Toned image.

Image: nantonov, Getty Images/iStockphoto

Differential privacy has become an integral way for data scientists to learn from the majority of their data while simultaneously ensuring that those results do not allow any individual’s data to be distinguished or re-identified.

To help more researchers with their work, IBM released the open-source Differential Privacy Library. The library “boasts a suite of tools for machine learning and data analytics tasks, all with built-in privacy guarantees,” according to Naoise Holohan, a research staff member on IBM Research Europe’s privacy and security team. 

“Our library is unique to others in giving scientists and developers access to lightweight, user-friendly tools for data analytics and machine learning in a familiar environment–in fact, most tasks can be run with only a single line of code,” Holohan wrote in a blog post on Friday

“What also sets our library apart is our machine learning functionality enables organizations to publish and share their data with rigorous guarantees on user privacy like never before.”

SEE: Data Circuit Installation or Change Checklist (TechRepublic Premium)

In an interview, Holohan explained that differential privacy has become so popular that for the first time in its 230-year history, the US Census will use differential privacy to keep the responses of citizens confidential when the data is made available.

Chris Sciacca, communications manager at IBM Research, added that the 2020 Census was a good example of how differential privacy can be used for any large data sets where you can do statistical analysis. 

“Healthcare data would be another area that it would be interesting for. Any large data sets where you want to keep the data anonymous but you don’t want to add so much noise to it that it’s useless. So here you’re just adding a little bit of noise where you can still get statistical anomalies to look at trends in large data sets,” Sciacca said.  

Differential privacy allows data collectors to use mathematical noise to anonymize information, and IBM’s library is special because it’s machine learning functionality enables organizations to publish and share their data with rigorous guarantees on user privacy.

“Originally, when we started looking at the space of open-source software and differential privacy, we noticed that there was a big gap in the market in terms of being able to do machine learning with differential privacy easily. There is a lot of work done in the literature that all the algorithms have been studied and made differentially private and solutions have been presented but there was no single repository or single library to go to do machine learning with differential privacy,” he said.

“We decided to build this library that, using existing packages in Python, allows you to build on top of them, and then you can do machine learning with differential privacy guarantees built-in. A lot of the commands you can execute in a single line of code, so it’s very user friendly. It’s easy to use and it can be integrated easily within scripts people have so there isn’t a lot of extra effort required.”

Last year, Google released its open-source differential privacy library and executives spoke about how they use it for a variety of their services. If you’ve ever looked at Google Maps and seen that fun chart of times when a business will be the busiest, you can thank differential privacy for it. 

Differential privacy allows Google to anonymously track data about when most people eat at a certain restaurant or shopped at a popular store and in 2014, they used it to improve their Chrome browser as well as Google Fi. 

Companies like Apple and Uber use versions of differential privacy to optimize their services while protecting the data of users.

Holohan said the IBM repository is already being used extensively for experimentation and to see what effect differential privacy has on machine learning algorithms. Academic institutions and bloggers are using the software to show how differential privacy works and he added that the library is being used internally at IBM to look at the impact of differential privacy on various applications. 

“It has applicability to basically any application of data so that gives a very good opportunity to do a lot of work in a lot of different areas. We have focused on machine learning because the application of privacy-preserving protocols to machine learning fits very well and machine learning is very prevalent in any use of data,” he said. 

“The next step is going to be allowing data scientists and analysts to be able to do a lot of  statistical analysis easily with differential privacy and our library is the first or a few steps along that path.”

Data, Analytics and AI Newsletter

Learn the latest news and best practices about data science, big data analytics, and artificial intelligence.
Delivered Mondays



Sign up today

Also see

Workday releases easily accessible deployment solutions for large enterprises

workday-releases-easily-accessible-deployment-solutions-for-large-enterprises

Workday Launch opens to qualified US large enterprises with a deployment solution to help organizations go live quickly on Workday.

Image: Workday

The more you know: It’s not only a network slogan, but represents how a deployment-solution company like Workday initially assesses a business’ needs. Workday Launch is now available to qualified US large enterprises (with plans to expand into other markets). When the service launched in 2017, it was designed for smaller customers.

Workday Launch is a preconfigured approach to deployment of the Workday software. According to the Workday website, it customizes a plan to a company’s approach, keeps it consistent, as well as ensures the deployment goes live on time. It also facilitates communication within the system.

SEE: Coronavirus: Critical IT policies and tools every business needs (TechRepublic Premium)

The decision to make the product available to large enterprises was born from the pandemic. 

“When COVID-19 became more widespread, we didn’t know what to expect from life in quarantine but more than three months later, we’ve started to adapt,” said Emily McEvilly, chief customer officer at Workday. McEvilly oversees the company’s customer experience organization, which includes professional services, education services, customer success, and Workday support; she’s responsible for deployment success and customer satisfaction. 

McEvilly pointed out that even though some things “haven’t changed at all, like laundry, paying bills, and cleaning house,” people still had to adapt to the new world of homeschooling and Zoom happy hours. And businesses, she said, have needs “that dramatically changed.” Welcome to the new normal, developed due to the coronavirus. 

Businesses, she said, had to learn to quickly to manage “everything remotely, while others have stayed consistent, like the demand for reliable finance and HR systems. However, the need for those systems to be flexible, cloud-based, and rock solid, has gone from important to critical.” 

Critically, she added, ‘Today, many companies are looking for new finance and HCM solutions and don’t have the luxury of time for a lengthy deployment. They need functionality they can use fast.”

SEE: Life after lockdown: Your office job will never be the same–here’s what to expect (cover story PDF) (TechRepublic)

Because of the preconfigured head-start, risk is limited, McEvilly said. Clients are given “a predictable timeframe.” Once Workday Launch prepares a prototype, the enterprise can expand and refine the preconfigured prototype to ensure the most appropriate match.

Highlights of Workday Launch

Each prepared package comes with features proven popular in previous deployments. A preconfigured tenant makes the launch happen faster. Since clients can see that quickly produced data “in action,” any decisions can be carefully calculated, which limits risks and cuts the margin for error. 

The process: an interested large enterprise chooses a package, add-ons, and integration requirements. Once a package is “up and running,” the business is provided with resources to accommodate changes within a company, including growth. 

“As the world continues to change around us, it’s important to remember that some things don’t change,” McEvilly said. Workday’s customers “influence every investment and decision we make. Expanding this program allows more customers to do the same.”

Executive Briefing Newsletter

Discover the secrets to IT leadership success with these tips on project management, budgets, and dealing with day-to-day challenges.
Delivered Tuesdays and Thursdays



Sign up today

Also see