Apheris is a platform for federated & privacy-preserving data science

Securely analyze data from multiple parties while keeping proprietary information private

Illustration of two companies in a data ecosystem

The Apheris Platform is the only enterprise-grade solution that covers the full data science workflow & collaboration process, end-to-end

Privacy & IP Protection

Leverage the full potential of partnerships without ever compromising the privacy or IP of any data or model

Compliance

Reduce risk and accelerate time-to-market with streamlined compliance frameworks and processes

Security

Ensure end-to-end protection of all assets with a platform that is designed to be foundationally secure

Enabling trusted collaborations on all scales
by ensuring data security, privacy, and IP protection

POSSIBILITIES One simple platform for your most secure data collaborations

Below are the various ways that your data collaborations can take shape

Internal
Collaborate across geographies

BENEFITS 1. Unlock combined insights 2. Empower truly secure data collaboration 3. Scale AI and capture exponential returns

One-to-One
Collaborate with external partners

BENEFITS 1. Combine knowledge to power more valuable AI 2. Establish trust and confidence in partnerships 3. Change the ways you will compete in the future

One-to-Many
Collaborate with multiple partners

BENEFITS 1. Create new revenue-generating business models 2. Mitigate risk and leverage data for valuable AI 3. Outpace competition and accelerate growth

Data Ecosystem
Build data collaborations on global scale

BENEFITS 1. Reach economies of scale by spreading profits & costs 2. Stay up to date with legislation 3. Operationalize AI and become a leader in your industry

Our CEO Robin explains how Apheris can help you to unlock the full potential of your data

Video thumbnail with Robin Röhm

How our platform works




1
Data Owners connect data
Create Nodes
2
Data Scientist develops model
Add Data
3
Privacy approval
Create Asset Policies
4
Explore Available Data
5
Model release
Run Federated Computations
6
Extract value & get insights
Get Insights
1
Data Providers connect data
Create Nodes

Create Nodes

  • Secure Nodes are physically isolated and confidential environments where data always stays protected.
  • Private data never leaves its Node and all data science computations happen exclusively within it.
2
Data Scientist develops model
Add Data

Add Data

  • Add a dataset to a workspace by selecting a set of files.
  • Describe data to understand the scope and origin.
  • Add or generate representative test data to enable third parties to explore your data in a privacy-preserving manner.
3
Privacy approval
Create Asset Policies

Create Asset Policies

  • Grant data consumers the permission to perform certain operations on a specified list of datasets.
  • Set fine-grained privacy controls.
4
Federated and private training
Explore Available Data

Explore Available Data

  • Explore data characteristics through metadata, representative test data and privacy-preserving statistics computations.
  • Build your federated computations and test it locally.
5
Model release
Run Federated Computations

Run Federated Computations

  • Execute the data science experiment.
  • Our propriertary Privacy Guard enforces specific privacy requirements.
  • Computations are orchestrated across selected datasets in their respective nodes.
  • Node results are aggregated and returned to the user.
6
Extract value & Get insights
Get Insights

Get Insights

  • Retrieve the results from the federated computation.
  • Analyze the results to generate business insights.

Create data science workflows with built-in privacy protection

Apheris enables the secure analysis of data across organizations while keeping proprietary information private. Computations are executed locally – meaning data never leaves the local environment and data privacy is preserved throughout the entire process. We use cutting-edge technologies to provide mathematical guarantees for privacy preservation.

Secure multiparty computation

Compute a joint function on multiple private inputs, where no party learns anything extra about any of the other parties' inputs.

Our awesome features
Differential privacy

Introduce random noise into the results of queries on underlying confidential data so that observers cannot reconstruct the original data.

Our awesome features
Privacy-preserving record linkage

Match data records that belong to the same entity (e.g., person) without revealing the identity of the entity.

Our awesome features
Homomorphic encryption

Encrypt data so that computation is possible on the ciphertext – the decrypted result should match the computation on the plaintext.

Our awesome features

Ready to accelerate your collaborations

Illustration of a privacy preserving data ecosystem with Apheris
Traceability & Auditability

Apheris ensures traceability of all statistics and ML operations across partners to comply internally and with GDPR or other laws and regulations.

Enterprise scalability

The Apheris Platform has been designed
for big data processing and can support cloud, multi-cloud, and hybrid environments.

Enterprise-grade security

With the highest security standards, the Apheris Platform has been proven to protect enterprise-grade datasets belonging to the world's largest organizations.

Interested in Secure Multi-Partner Data Collaborations for your industry?

Get in touch with our AI specialists for a scoping session