Dropnir

Wodan’s software solution “Dropnir” sits in between your application and the AI model. Your application talks to Dropnir, we encrypt your data on-premises and talk to the model without ever decrypting your data.

Dropnir leverages cutting-edge technologies like Fully Homomorphic Encryption (FHE) and Zero-Knowledge Proofs (ZKP) to ensure unparalleled data privacy and security in AI applications.

With FHE, users can encrypt their data, transmit it securely to the AI model, and allow computations directly on encrypted data—ensuring that sensitive information remains protected throughout the process. Even the AI model provider cannot access the plaintext data, as only the user with encryption keys can decrypt the results.

Zero-Knowledge Proofs (ZKP) add an additional layer of security by providing cryptographic verification that the AI model executed the intended request with integrity. ZKP ensures compliance and trust without exposing proprietary or sensitive information.

Dropnir integrates seamlessly with Wodan AIs SaaS platform, which offers advanced metrics collection for monitoring data and request volumes while enabling scalable pay-per-use billing for optimal efficiency.

Dropnir serves as a thin layer between the application and the model.

As a user, you don’t notice any difference in behavior from talking to the model or to Dropnir.

The software is easy to install (as a container) and serves as a thin API layer.

The model performs its magic, whatever it is meant to do, but it does it over encrypted data!

The model then sends an answer back to Dropnir, again fully encrypted. The owner of the model was never able to view the request, the data, or the answer.

Dropnir decrypts the result using the private key from the customer, and provides a clear-text readable answer to the customer’s application.

Wodan’s SaaS platform is used for metrics collection on how much data and requests are transmitted through Dropnir, and provides easy chargeback.

Use Case

THE PROBLEM

THE SOLUTION: FHE + ZKPs = ZKML