cl-au logo
Story image

Google's Federated Learning tech gets privacy enhancements

23 Sep 2019

Lots of organisations are starting to blend artificial intelligence into their websites and apps. Customers expect a smart interface and experience but are hesitant about privacy.

Google is a leading provider of the underlying open-source technology that is used in artificial intelligence by organisations' developers.

First, they open-sourced TensorFlow, which helped those developers with machine learning projects. Then in August, they introduced Federated Learning. You can read our full explanation of Federated Learning in layman's terms here.

With Federated Learning the training data for the machine learning is cleverly kept on the individual device (for example, a smartphone). This means only insights learnt from that training data is submitted centrally, instead of the data itself.

This really is a smart technology that helps artificial intelligence but without privacy issues.

One chink in this approach is the idea of re-identification. That an organisation or system can take these anonymised insights that got submitted centrally and extrapolate back to the full data. Essentially removing the anonymity and possibly doing this without the user knowing.

The solution to this is an approach called Differential Privacy, which makes it difficult or impossible for an individual's private data to be re-identified.

"Differentially-private data analysis is a principled approach that enables organisations 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. This type of analysis can be implemented in a wide variety of ways and for many different purposes. For example, if you are a health researcher, you may want to compare the average amount of time patients remain admitted across various hospitals in order to determine if there are differences in care. Differential privacy is a high-assurance, analytic means of ensuring that use cases like this are addressed in a privacy-preserving manner." says Miguel Guevara, Product Manager, Privacy and Data Protection Office, Google.

Here are some of the critical features of the library:

  • Statistical functions: Most common data science operations are supported by this release. Developers can compute counts, sums, averages, medians, and percentiles using our library.
  • Rigorous testing: Getting differential privacy right is challenging. Besides an extensive test suite, we've included an extensible 'Stochastic Differential Privacy Model Checker library' to help prevent mistakes.
  • Ready to use: The real utility of an open-source release is in answering the question "Can I use this?" That's why we've included a PostgreSQL extension along with common recipes to get you started. We've described the details of our approach in a technical paper that we've just released today.
  • Modular: We designed the library so that it can be extended to include other functionalities such as additional mechanisms, aggregation functions, or privacy budget management.

Google uses differential privacy already in Google Maps and Chrome since 2014.

The new differential privacy library is available on GitHub here.

Link image
Phishing campaigns show no sign of slowing down
Even though the 'phishing explosion' in March and April has passed, businesses and individuals are still at serious risk. The game has changed - make sure you're up to date and protected.More
Download image
The humble email is still the biggest security risk - report
Email’s popularity is a double-edged sword – not only is it the tool that we all use to communicate in business, it continues to be the most common way that cyberthreats pierce a business.More
Story image
Deloitte Australia, Qrious and Velocity big winners at Snowflake APAC partner awards
"These awards recognise the partners who have led new customer acquisition, established Snowflake in new markets and invested heavily to bring Snowflake solutions and service offerings to market over the last year."More
Download image
Ultimate security: The best authentication just got better
Cloud applications can hold sensitive data, and top-notch authentication is key. But having separate tools for separate applications can be cumbersome - here's how to overcome that.More
Story image
Australian supercomputer Gadi ranks 25 in Global 500
“Gadi represents a milestone for Australian research. We are pleased to continue our long-standing relationship with Fujitsu and its network to offer Australian researchers world-class computing resources to take us into the next decade.”More
Story image
HP Inc pledges to eliminate 75% of single-use plastic by 2025
This transition from plastic to molded fibre has already eliminated 933 tonnes of hard-to-recycle expanded plastic foam last year, according to HP.More