The Apheris Resource Library

Gain insights in establishing private, secure, governed ML, and unlocking greater value from data through collaboration

Featured Resources

Privacy and Security Whitepaper

Enabling federated research for life sciences

Navigating the EU AI Act: compliance foundations for a new era

Privacy and Security Whitepaper

Latest Blog Posts

The EU AI Act: Understanding and Preparing for Compliance

Exploring the EU AI Act, a pivotal regulation addressing AI's multifaceted nature, this blog outlines risk levels, high-risk system requirements, and preparation for compliance. Apheris's solution for various governance, privacy, and security obligations is highlighted, emphasizing a shared commitment to responsible AI.

Hey, your data is on mute

Reaching universal agreement on how to regulate AI is impossible. But a carefully designed cyclical process can lead to efficiencies in an enterprise's journey towards trustworthy, accountable, and sustainable AI. In this blog, I navigate the regulation space through the eyes of a data custodian.

Enlightening Dark Data

There is so much useful data around us. Yet most data is not accessible for machine learning or other large scale analytics. In this article, we will explore why this is and what needs to be in place to enlighten this dark data.

The EU AI Act: Understanding and Preparing for Compliance

Exploring the EU AI Act, a pivotal regulation addressing AI's multifaceted nature, this blog outlines risk levels, high-risk system requirements, and preparation for compliance. Apheris's solution for various governance, privacy, and security obligations is highlighted, emphasizing a shared commitment to responsible AI.

Publications

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.

Read the Publication

Asymmetric Private Set Intersection and Private Vertical Federated Machine Learning

We present a multi-language, cross-platform, open-source library for asymmetric private set intersection (PSI) and PSI-Cardinality (PSI-C). Our protocol combines traditional DDH-based PSI and PSI-C protocols with compression based on Bloom filters that helps reduce communication in the asymmetric setting.

Read the Publication

PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN

We introduce PyVertical, a framework supporting vertical federated learning using split neural networks. The proposed framework allows a data scientist to train neural networks on data features vertically partitioned across multiple owners while keeping raw data on an owner's device.

Read the Publication

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.

Read the Publication