Confidential AI

Privacy-Preserving
Machine Learning

Use Zama Concrete ML to leverage the power of Machine Learning while ensuring your users' privacy and data security with Fully Homomorphic Encryption (FHE).

Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation
Read Concrete ML documentation

FHE Unlocks a Myriad of New Use Cases with Encrypted Computation

and opens a new world for confidential AI.

Healthcare

Improve patient care while maintaining privacy by allowing secure, confidential data sharing between healthcare providers.

Finance

Facilitate secure financial data analysis for risk management and fraud detection, keeping client information encrypted and safe.

Advertising

Create targeted advertising and campaign insights in a post-cookie era, ensuring user privacy through encrypted data analysis.

Defense

Enable data collaboration between different agencies, while keeping it confidential from each other, enhancing efficiency and data security, without revealing secrets.

Biometrics

Give the ability to create user authentication applications without having to reveal their identities.

Government

Enable governments to create digitized versions of their services without having to trust cloud providers.

Implement Machine Learning Algorithms Operating on Encrypted Data Using FHE

Concrete ML enables the handling of sensitive data in a secure manner, so data scientists can leverage the power of Machine Learning for new use cases where the data needs to be protected.

Private inference

Run secure, privacy-preserving predictions using your ML models over encrypted data.

Private training

Train models over encrypted datasets, owned by parties that don't trust each other.

Secure collaboration

Collaborate on sensitive data with untrusted third parties without compromising privacy inside data clean rooms.

Private LLMs and IP protection

Unleash the power of LLMs like ChatGPT on your data while keeping important information confidential.

Leverage the Power of FHE Without Having to Learn Cryptography

Ease of use for data-scientists
Use familiar APIs from scikit-learn and PyTorch to automatically convert machine learning models into their FHE equivalent.

Support for various models and customization
Concrete ML comes with built-in models that are ready-to-use and FHE-friendly, mimicking the user interfaces of their scikit-learn and XGBoost counterparts.

Read documentation
# Example for Tree-based Models
from concrete.ml.sklearn import XGBClassifier

model = XGBClassifier(n_bits=8)
model.fit(X_train, y_train)
model.predict(X_test)
model.compile(X_train)
model.predict(Xtest, fhe="simulate")
model.predict(X_test, fhe="execute")

# Example for Linear Models
from concrete.ml.sklearn import LogisticRegression

model = LogisticRegression(n_bits=12)
model.fit(X_train, y_train)
model.predict(X_test)
model.compile(X_train)
model.predict(X_test, fhe="simulate")
model.predict(X_test, fhe="execute")
def f(df_a, df_b):
  # df_a schema is {
  #     'name': pd.Series(dtype='encrypted_str'),
  #     'income_per_month': pd.Series(dtype='encrypted_uint32')
  #     'birthdate': pd.Series(dtype='encrypted_date')
  # }
  # df_b schema is {
  #     'name': pd.Series(dtype='encrypted_str'),
  #     'credit_risk': pd.Series(dtype='encrypted_uint4')
  # }
  df_join = df_a.align(df_b, join="inner", axis=1)
  df_filt = df_join.query("birthdate > 1992-01-01")
  classifier = SGDClassifier(fit_encrypted=True)
  classifier.fit(df_filt)
  return classifier.coef_

Collaborative Secure Computation

Opening up new avenues for collaborative research and development across various sectors.
Create data clean rooms where you can encrypt and process information from multiple sources, ensuring each participant only sees the final results, not others' sensitive data. Ideal for finance, healthcare, research, and more – where collaboration is key, but data security is crucial.

Read documentation

Machine Learning Model Support

Concrete ML provides for several of the most popular and traditional models.

Linear Models

- Linear Regression
- Logistic Regression
- Generalized Linear Models
- SVM
- ElasticNet
- Lasso
- Ridge

Tree-based Models

- Decision Trees
- Random Forest
- XGBoost




Neureal Networks

- Built-in Multi-Layer Perception
- CNNs
- VGG


Versatility by Design — Concrete, a Modular Framework

Concrete ML is built on top of Concrete, Zama's open source FHE compiler, making it a very modular framework, and ready to integrate future innovations.

Read more about Concrete: Zama's FHE compiler.

More Resources

Read our latest privacy-preserving machine learning blog posts and learn more with our developer tutorials and presentations.

Ready to implement FHE?

Deep dive into our tech or contact our team to get started.

Are you a developer?

Everything we do at Zama is open source, check our Github libraries, and learn how to implement FHE with our developer resources.
See on Github

Contact our sales team

Learn how you can leverage the power of Zama's fhEVM Coprocessor and Threshold Key Management Service for your tokenization project.
Book a demo