Concrete ML: Privacy Preserving ML framework built on top of Concrete, with bindings to traditional ML frameworks.
OTHER License
Bot releases are hidden (Show)
Published by bcm-at-zama almost 2 years ago
This Concrete-ML release adds support for:
New tutorials show how to train large neural networks either from scratch or by transfer learning, how to convert them into an FHE-friendly models and finally how to evaluate them in FHE and with simulation. The release adds tools that leverage FHE simulation to select optimal parameters that speed up the inference of neural networks. Python 3.10 support is included in this release.
Docker Image: zamafhe/concrete-ml:v0.6.1
pip: https://pypi.org/project/concrete-ml/0.6.1
Documentation: https://docs.zama.ai/concrete-ml
4f112ca
)aede49b
)35715e2
)42405c5
)637c272
)a52d917
)b54fcac
)1780cd5
)52e87b7
)b7fa8c1
)f2dfc3e
)1495214
)5196c68
)Published by fd0r almost 2 years ago
The main objective of this release is to fix some issues with recent updates in dependencies, and to extend the support from python 3.7.14 to python 3.7.1.
Docker Image: zamafhe/concrete-ml:v0.5.1
pip: https://pypi.org/project/concrete-ml/0.5.1
Documentation: https://docs.zama.ai/concrete-ml
eb212bf
)ebd06b4
)Published by fd0r almost 2 years ago
The main objective of this release is to add python 3.7 support.
Docker Image: zamafhe/concrete-ml:v0.5.0
pip: https://pypi.org/project/concrete-ml/0.5.0
Documentation: https://docs.zama.ai/concrete-ml
fef90d1
)89668bf
)24e8f88
)14502f0
)Published by fd0r about 2 years ago
This version of Concrete-ML adds more support for quantization-aware training neural networks, adds decision tree-ensemble regressors, and includes additional linear regression models. For custom models, first-class support for Brevitas quantization aware training neural networks was added: a dedicated function imports models containing Brevitas layers directly. Design rules for these neural networks using Brevitas are detailed in the documentation. Moreover, quantization aware training is now the default for built-in neural networks, giving good accuracy out-of-the-box, with low bit-widths for weights, activations, and accumulators. Tree-based RandomForest and XGBoost regression models are now supported, while the linear regressors are complemented by the Ridge, Lasso, and ElasticNet models. Many usage example notebooks were added, showing how to use the new models, and also showing more complex use-cases such as sentiment analysis, MNIST classification, and Kaggle Titanic dataset classification.
Docker Image: zamafhe/concrete-ml:v0.4.0
pip: https://pypi.org/project/concrete-ml/0.4.0
Documentation: https://docs.zama.ai/concrete-ml/v/0.4/
174f6f7
)fd684df
)5ed9476
)0c7853c
)9736557
)5b12d53
)675c7b3
)13d8d74
)f708ba7
)d162cd6
)922d60e
)a15fe9d
)90a50b4
)1dd9ba3
)d214216
)f45b79f
)985d0d5
)accfd3e
)0a0534a
)081d8f9
)88fed0b
)b2d81e4
)49717bf
)ba06e5e
)30b2b27
)4419438
)Published by andrei-stoian-zama about 2 years ago
Concrete-ML now gives the user the possibility to deploy models in a client-server setting, separating encryption and decryption from execution, which can now be done by a remote machine. The release also adds support for new models and for new neural network layers, but also allows importing ONNX directly, thus supporting some keras/tensorflow models. Furthermore, this release provides some support for importing Quantization Aware Training neural networks, which contain quantizers in the operation graph and can be built with brevitas.
Docker Image: zamafhe/concrete-ml:v0.3.0
pip: https://pypi.org/project/concrete-ml/0.3.0
Documentation: https://docs.zama.ai/concrete-ml
9b69e73
)fe03441
)c732d15
)6f887d0
)64c4512
)6c40a0c
)3c2a68a
)76e142c
)1fa74f7
)d6880ce
)c1bb947
)fae3dc5
)8e8e025
)3ce338e
)e43ce5c
)09eefa5
)249c712
)c5f215f
)950cc6c
)7969739
)f939149
)40f1ef9
)26b2221
)206caa5
)97ccfc0
)02e497c
)111419e
)f257def
)b614285
)baa3b4d
)e5e3205
)68ae7d0
)9b63c8a
)9430ba6
)972d05e
)fb9b409
)34652ce
)99ff1e7
)1c6f571
)972d464
)0a44853
)Published by bcm-at-zama about 2 years ago
Fixing issues to updates in some dependancies that we used with a not-fixed version
Docker Image: zamafhe/concrete-ml:v0.2.1
pip: https://pypi.org/project/concrete-ml/0.2.1
Documentation: https://docs.zama.ai/concrete-ml
4dd46cf
)fa90586
)38c1062
)Published by jfrery over 2 years ago
Use Concrete Numpy 0.5.
Add multi-class classification to XGBoost.
Fixing some minor broken links or issues.
Docker Image: zamafhe/concrete-ml:v0.2.0
pip: https://pypi.org/project/concrete-ml/0.2.0
Documentation: https://docs.zama.ai/concrete-ml/ (old link https://docs.zama.ai/concrete-ml/0.2.0 has been moved)
run
method is renamed to encrypt_run_decrypt
after changes in Concrete-Numpy 0.5.0. Individual APIs to encrypt/run/decrypt separately will be available in a further release of Concrete-MLecbb26e
)ee5987b
)9247f35
)set_version_and_push
command to the makefile (ab853c2
)df0a64d
)bf52514
).forward_fhe.run()
has been renamed into .forward_fhe.encrypt_run_decrypt()
(ecbb26e
)f1bafff
)Published by bcm-at-zama over 2 years ago
Use Concrete Numpy 0.4.
Fixing some minor broken links or issues.
Docker Image: zamafhe/concrete-ml:v0.1.1
pip: https://pypi.org/project/concrete-ml/0.1.1
Documentation: https://docs.zama.ai/concrete-ml/0.1.1
6f9651e
)27839be
)349c947
)Published by bcm-at-zama over 2 years ago
First release of Concrete-ML package
Docker Image: zamafhe/concrete-ml:v0.1.0
pip: https://pypi.org/project/concrete-ml/0.1.0
Documentation: https://docs.zama.ai/concrete-ml/0.1.0
0478854
)1367d4e
)d95af58
)28ea1eb
)a057881
)7b5c118
)4acca2f
)1ffcdfb
)321d151
)596d16e
)1a78593
)8e62cf8
)8fcd307
)5630f17
)17d5cc4
)9aaeec5
)699603d
)9de2ba4
)4a173ee
)d048077
)36df77e
)9719c08
)85c25df
)44ec0b3
)060a4c6
)ad32509
)ae8313e
)e73a514
)609f1df
)01c3a4a
)716fc43
)1fa530d
)da91e40
)4b9927a
)a0c56d7
)65f0a6e
)ecdeb50
)d58910d
)e5d7440
)8b051df
)73d885c
)f64c3bf
)ca9c6e5
)d66d7bf
)b63eca2
)bb568e2
)072bd63
)db163f5
)d1cfc4e
)a525e8b
)847db99
)8096acc
)8da0988
)b9f1206
)ab2a821
)3673584
)3053085
)c6cee4e
)7b92bd8
)7c4bd0e
)2ed49b6
)7f521f9
)69e9b15
)9d07f5c
)798662f
)7d52750
)82abb12
)1f7b92e
)6595495
)182084f
)84a65e4
)65aa1b2
)51c0bc5
)1c527be
)9fe43bf
)11c5616
)cc3c0b6
)0c164f5
)45d4fca
)ff771aa
)0d1e672
)21d9a77
)029237a
)b836811
)436e71e
)33b044f
)6b3ca04
)ed9ee3f
)c4e73ec
)4508282
)1046cc2
)4f68f3f
)05103b3
)95a1669
)beef6c9
)51ed1be
)4d51c96
)37227c6
)833d6e4
)make conformance
(bff86ca
)179e235
)c977a32
)6307508
)e3e0234
)858f193
)eff1b15
)2b16560
)ce0d24b
)0306cee
)a440de3
)4fb1445
)16978b6
)235322a
)c29504a
)