Detection and Prevention of Unauthorized Knowledge Distillation in Machine Learning APIs

A system that detects and prevents unauthorised knowledge distillation in machine learning APIs.

A system that detects and prevents unauthorised knowledge distillation in machine learning APIs. It is offered as a reference project: a complete, worked example of how a system like this is designed, built and evaluated, so that a developer can study it, run it and learn from it.

It suits learners who want practical security experience: understanding the threat, building the defence or detector, testing it against realistic attacks and reporting the results.

The main parts are a realistic threat model, the detection or protection mechanism itself, testing against sample attacks, and reporting and alerting of findings. The reference build uses Python, scikit-learn, Wireshark, and OpenSSL, with a clear project structure, setup instructions and sample data so that it can be run and extended.