privacylens

Audits ML models in a few lines of code for privacy leakage and memorization

Desktopfree

privacylens is a free, open-source privacy auditing toolkit that runs five automated checks against a trained ML model to detect whether it memorized private training data, including membership inference risk, PII leakage in predictions, and an estimated differential-privacy loss. It generates standalone HTML compliance reports and can gate Azure ML pipelines or CI/CD builds. It's for ML engineers and teams who need to verify, before deployment, that a model trained on sensitive data isn't leaking it back out.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of privacylens - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim privacylens to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether privacylens (or something else) actually fits.

Try a problem