# Compute on encrypted training data supported?

**URL:** <https://openfhe.discourse.group/t/compute-on-encrypted-training-data-supported/576>\
**Category:** Library Questions\
**Created:** [May 23, 2023, 7:53am UTC](https://openfhe.discourse.group/t/compute-on-encrypted-training-data-supported/576 "2023-05-23T07:53:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Naro](https://avatars.discourse-cdn.com/v4/letter/n/5f9b8f/32.png) [@Naro](https://openfhe.discourse.group/u/Naro)\
**Post date:** [May 23, 2023, 7:53am UTC](https://openfhe.discourse.group/t/compute-on-encrypted-training-data-supported/576/1 "2023-05-23T07:53:58Z")

</div>

Hi there,

i like to know if it is possible to train a model on encrypted data in OpenFHE rather than using plain data for training and encrypted data for computing a result.

Best regards

---

<div class="post-metadata">

**Author:** ![iquah](https://yyz1.discourse-cdn.com/flex031/user_avatar/openfhe.discourse.group/iquah/32/8_2.png) [@iquah](https://openfhe.discourse.group/u/iquah)\
**Post date:** [May 23, 2023, 4:16pm UTC](https://openfhe.discourse.group/t/compute-on-encrypted-training-data-supported/576/2 "2023-05-23T16:16:54Z")

</div>

Yes, it is! Check out [GitHub - openfheorg/openfhe-logreg-training-examples: Examples of Logistic Regression Training using Nesterov Accelerated Gradient Descent](https://github.com/openfheorg/openfhe-logreg-training-examples)