Whitepaper: Privacy and Security

Privacy and security considerations are an important part of adopting a federated infrastructure for machine learning and analytics. This whitepaper outlines the various security techniques and privacy controls used by Apheris to safely collaborate and build data applications and AI across organizational and geographical boundaries.

This whitepaper outlines:

The privacy and security landscape, and how Apheris operates within it
Defining attack vectors and threat models as the basis for a privacy and security strategy
Using the 5 Safes as a framework for privacy and security in federated ML and analytics
Practical advice for making the move to a federated data infrastructure including a basic maturity assessment for assessing readiness

Recommended reading


The Three Adoption Stages of Privacy-enhancing Technologies (And Why We Are Stuck on Level Two)

PETs are massively changing how we operate, and how we have to think about the data and AI landscape. Introducing such a game-changer into large enterprises has to be done with the highest precision, and a lot of foresight.


Challenges with implementing federated learning

Explore some of the common challenges organizations face when implementing federated learning and key considerations that can help them overcome those challenges and reap the rewards of working with federated data.


Security of AI  Systems: Fundamentals

Advising the German Federal Office for Information Security on the Security of AI-Systems, Apheris provides an overview on attack vectors and threats of AI systems where external data is used or trained models are exposed to third parties. Recommendations are derived on how to systematically safeguard and test AI-systems.