Skip to content

Commit de77cd7

Browse files
ryanlehryanleh
committed
Initial commit
0 parents  commit de77cd7

File tree

279 files changed

+54530
-0
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

279 files changed

+54530
-0
lines changed

‎.gitattributes

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
rust/protocols-sys/c++/SEAL/* linguist-vendored=true

‎.gitignore

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
# Python
2+
**/__pycache__
3+
4+
# Rust
5+
# *.lock
6+
**/target
7+
target
8+
**/*.rs.bk
9+
10+
# C++
11+
**/SEALConfig.cmake
12+
**/SEALConfigVersion.cmake
13+
**/SEALTargets.cmake
14+
system/c++/SEAL/native/src/seal/util/config.h
15+
**/CMakeCache.txt
16+
**/CMakeFiles
17+
**/Makefile
18+
**/.config
19+
**/autom4te.cache/*
20+
**/cmake_install.cmake

‎LICENSE-APACHE

Lines changed: 201 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,201 @@
1+
Apache License
2+
Version 2.0, January 2004
3+
http://www.apache.org/licenses/
4+
5+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6+
7+
1. Definitions.
8+
9+
"License" shall mean the terms and conditions for use, reproduction,
10+
and distribution as defined by Sections 1 through 9 of this document.
11+
12+
"Licensor" shall mean the copyright owner or entity authorized by
13+
the copyright owner that is granting the License.
14+
15+
"Legal Entity" shall mean the union of the acting entity and all
16+
other entities that control, are controlled by, or are under common
17+
control with that entity. For the purposes of this definition,
18+
"control" means (i) the power, direct or indirect, to cause the
19+
direction or management of such entity, whether by contract or
20+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
21+
outstanding shares, or (iii) beneficial ownership of such entity.
22+
23+
"You" (or "Your") shall mean an individual or Legal Entity
24+
exercising permissions granted by this License.
25+
26+
"Source" form shall mean the preferred form for making modifications,
27+
including but not limited to software source code, documentation
28+
source, and configuration files.
29+
30+
"Object" form shall mean any form resulting from mechanical
31+
transformation or translation of a Source form, including but
32+
not limited to compiled object code, generated documentation,
33+
and conversions to other media types.
34+
35+
"Work" shall mean the work of authorship, whether in Source or
36+
Object form, made available under the License, as indicated by a
37+
copyright notice that is included in or attached to the work
38+
(an example is provided in the Appendix below).
39+
40+
"Derivative Works" shall mean any work, whether in Source or Object
41+
form, that is based on (or derived from) the Work and for which the
42+
editorial revisions, annotations, elaborations, or other modifications
43+
represent, as a whole, an original work of authorship. For the purposes
44+
of this License, Derivative Works shall not include works that remain
45+
separable from, or merely link (or bind by name) to the interfaces of,
46+
the Work and Derivative Works thereof.
47+
48+
"Contribution" shall mean any work of authorship, including
49+
the original version of the Work and any modifications or additions
50+
to that Work or Derivative Works thereof, that is intentionally
51+
submitted to Licensor for inclusion in the Work by the copyright owner
52+
or by an individual or Legal Entity authorized to submit on behalf of
53+
the copyright owner. For the purposes of this definition, "submitted"
54+
means any form of electronic, verbal, or written communication sent
55+
to the Licensor or its representatives, including but not limited to
56+
communication on electronic mailing lists, source code control systems,
57+
and issue tracking systems that are managed by, or on behalf of, the
58+
Licensor for the purpose of discussing and improving the Work, but
59+
excluding communication that is conspicuously marked or otherwise
60+
designated in writing by the copyright owner as "Not a Contribution."
61+
62+
"Contributor" shall mean Licensor and any individual or Legal Entity
63+
on behalf of whom a Contribution has been received by Licensor and
64+
subsequently incorporated within the Work.
65+
66+
2. Grant of Copyright License. Subject to the terms and conditions of
67+
this License, each Contributor hereby grants to You a perpetual,
68+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69+
copyright license to reproduce, prepare Derivative Works of,
70+
publicly display, publicly perform, sublicense, and distribute the
71+
Work and such Derivative Works in Source or Object form.
72+
73+
3. Grant of Patent License. Subject to the terms and conditions of
74+
this License, each Contributor hereby grants to You a perpetual,
75+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76+
(except as stated in this section) patent license to make, have made,
77+
use, offer to sell, sell, import, and otherwise transfer the Work,
78+
where such license applies only to those patent claims licensable
79+
by such Contributor that are necessarily infringed by their
80+
Contribution(s) alone or by combination of their Contribution(s)
81+
with the Work to which such Contribution(s) was submitted. If You
82+
institute patent litigation against any entity (including a
83+
cross-claim or counterclaim in a lawsuit) alleging that the Work
84+
or a Contribution incorporated within the Work constitutes direct
85+
or contributory patent infringement, then any patent licenses
86+
granted to You under this License for that Work shall terminate
87+
as of the date such litigation is filed.
88+
89+
4. Redistribution. You may reproduce and distribute copies of the
90+
Work or Derivative Works thereof in any medium, with or without
91+
modifications, and in Source or Object form, provided that You
92+
meet the following conditions:
93+
94+
(a) You must give any other recipients of the Work or
95+
Derivative Works a copy of this License; and
96+
97+
(b) You must cause any modified files to carry prominent notices
98+
stating that You changed the files; and
99+
100+
(c) You must retain, in the Source form of any Derivative Works
101+
that You distribute, all copyright, patent, trademark, and
102+
attribution notices from the Source form of the Work,
103+
excluding those notices that do not pertain to any part of
104+
the Derivative Works; and
105+
106+
(d) If the Work includes a "NOTICE" text file as part of its
107+
distribution, then any Derivative Works that You distribute must
108+
include a readable copy of the attribution notices contained
109+
within such NOTICE file, excluding those notices that do not
110+
pertain to any part of the Derivative Works, in at least one
111+
of the following places: within a NOTICE text file distributed
112+
as part of the Derivative Works; within the Source form or
113+
documentation, if provided along with the Derivative Works; or,
114+
within a display generated by the Derivative Works, if and
115+
wherever such third-party notices normally appear. The contents
116+
of the NOTICE file are for informational purposes only and
117+
do not modify the License. You may add Your own attribution
118+
notices within Derivative Works that You distribute, alongside
119+
or as an addendum to the NOTICE text from the Work, provided
120+
that such additional attribution notices cannot be construed
121+
as modifying the License.
122+
123+
You may add Your own copyright statement to Your modifications and
124+
may provide additional or different license terms and conditions
125+
for use, reproduction, or distribution of Your modifications, or
126+
for any such Derivative Works as a whole, provided Your use,
127+
reproduction, and distribution of the Work otherwise complies with
128+
the conditions stated in this License.
129+
130+
5. Submission of Contributions. Unless You explicitly state otherwise,
131+
any Contribution intentionally submitted for inclusion in the Work
132+
by You to the Licensor shall be under the terms and conditions of
133+
this License, without any additional terms or conditions.
134+
Notwithstanding the above, nothing herein shall supersede or modify
135+
the terms of any separate license agreement you may have executed
136+
with Licensor regarding such Contributions.
137+
138+
6. Trademarks. This License does not grant permission to use the trade
139+
names, trademarks, service marks, or product names of the Licensor,
140+
except as required for reasonable and customary use in describing the
141+
origin of the Work and reproducing the content of the NOTICE file.
142+
143+
7. Disclaimer of Warranty. Unless required by applicable law or
144+
agreed to in writing, Licensor provides the Work (and each
145+
Contributor provides its Contributions) on an "AS IS" BASIS,
146+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147+
implied, including, without limitation, any warranties or conditions
148+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149+
PARTICULAR PURPOSE. You are solely responsible for determining the
150+
appropriateness of using or redistributing the Work and assume any
151+
risks associated with Your exercise of permissions under this License.
152+
153+
8. Limitation of Liability. In no event and under no legal theory,
154+
whether in tort (including negligence), contract, or otherwise,
155+
unless required by applicable law (such as deliberate and grossly
156+
negligent acts) or agreed to in writing, shall any Contributor be
157+
liable to You for damages, including any direct, indirect, special,
158+
incidental, or consequential damages of any character arising as a
159+
result of this License or out of the use or inability to use the
160+
Work (including but not limited to damages for loss of goodwill,
161+
work stoppage, computer failure or malfunction, or any and all
162+
other commercial damages or losses), even if such Contributor
163+
has been advised of the possibility of such damages.
164+
165+
9. Accepting Warranty or Additional Liability. While redistributing
166+
the Work or Derivative Works thereof, You may choose to offer,
167+
and charge a fee for, acceptance of support, warranty, indemnity,
168+
or other liability obligations and/or rights consistent with this
169+
License. However, in accepting such obligations, You may act only
170+
on Your own behalf and on Your sole responsibility, not on behalf
171+
of any other Contributor, and only if You agree to indemnify,
172+
defend, and hold each Contributor harmless for any liability
173+
incurred by, or claims asserted against, such Contributor by reason
174+
of your accepting any such warranty or additional liability.
175+
176+
END OF TERMS AND CONDITIONS
177+
178+
APPENDIX: How to apply the Apache License to your work.
179+
180+
To apply the Apache License to your work, attach the following
181+
boilerplate notice, with the fields enclosed by brackets "[]"
182+
replaced with your own identifying information. (Don't include
183+
the brackets!) The text should be enclosed in the appropriate
184+
comment syntax for the file format. We also recommend that a
185+
file or class name and description of purpose be included on the
186+
same "printed page" as the copyright notice for easier
187+
identification within third-party archives.
188+
189+
Copyright [yyyy] [name of copyright owner]
190+
191+
Licensed under the Apache License, Version 2.0 (the "License");
192+
you may not use this file except in compliance with the License.
193+
You may obtain a copy of the License at
194+
195+
http://www.apache.org/licenses/LICENSE-2.0
196+
197+
Unless required by applicable law or agreed to in writing, software
198+
distributed under the License is distributed on an "AS IS" BASIS,
199+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200+
See the License for the specific language governing permissions and
201+
limitations under the License.

‎LICENSE-MIT

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
The MIT License (MIT)
2+
3+
Permission is hereby granted, free of charge, to any person obtaining a copy
4+
of this software and associated documentation files (the "Software"), to deal
5+
in the Software without restriction, including without limitation the rights
6+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7+
copies of the Software, and to permit persons to whom the Software is
8+
furnished to do so, subject to the following conditions:
9+
10+
The above copyright notice and this permission notice shall be included in
11+
all copies or substantial portions of the Software.
12+
13+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19+
THE SOFTWARE.

‎README.md

Lines changed: 146 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,146 @@
1+
<h1 align="center">Delphi</h1>
2+
3+
___Delphi___ is a Python, C++, and Rust library for **Secure Deep Neural Network Inference**
4+
5+
This library was initially developed as part of the paper *"[Delphi: A Cryptographic Inference Service for Neural Networks][delphi]"*, and is released under the MIT License and the Apache v2 License (see [License](#license)).
6+
7+
**WARNING:** This is an academic proof-of-concept prototype, and in particular has not received careful code review. This implementation is NOT ready for production use.
8+
9+
## Overview
10+
11+
This library implements a cryptographic system for efficient inference on general convolutional neural networks.
12+
13+
The construction utilizes an array of multi-party computation and machine-learning techniques, as described in the [Delphi paper][delphi].
14+
15+
## Directory structure
16+
17+
This repository contains several folders that implement the different building blocks of Delphi. The high-level structure of the repository is as follows.
18+
* [`python`](python): Example Python scripts for performing neural architecture search (NAS)
19+
20+
* [`rust/algebra`](rust/algebra): Rust crate that provides finite fields
21+
22+
* [`rust/crypto-primitives`](rust/crypto-primitives): Rust crate that implements some useful cryptographic primitives
23+
24+
* [`rust/experiments`](rust/experiments): Rust crate for running latency, bandwidth, throughput, accuracy, and memory usage experiments
25+
26+
* [`rust/neural-network`](rust/neural-network): Rust crate that implements generic neural networks
27+
28+
* [`rust/protocols`](rust/protocols): Rust crate that implements cryptographic protocols
29+
30+
* [`rust/protocols-sys`](rust/crypto-primitives): Rust crate that provides the C++ backend for Delphi's pre-processing phase and an FFI for the backend
31+
32+
In addition, there is a [`rust/bench-utils`](rust/bench-utils) crate which contains infrastructure for benchmarking. This crate includes macros for timing code segments and is used for profiling the building blocks of Delphi.
33+
34+
35+
## Build guide
36+
37+
The library compiles on the `nightly` toolchain of the Rust compiler. To install the latest version of Rust, first install `rustup` by following the instructions [here](https://rustup.rs/), or via your platform's package manager. Once `rustup` is installed, install the Rust toolchain by invoking:
38+
```bash
39+
rustup install nightly
40+
```
41+
42+
After that, use `cargo`, the standard Rust build tool, to build the library:
43+
```bash
44+
git clone https://github.com/mc2-project/delphi
45+
cd delphi
46+
cargo +nightly build --release
47+
```
48+
49+
This library comes with unit tests for each of the provided crates. Run the tests with:
50+
```bash
51+
cargo +nightly test
52+
```
53+
Benchmarks are included for the following crates:
54+
- [`algebra`](algebra)
55+
- [`crypto-primitives`](algebra)
56+
- [`neural-network`](algebra)
57+
58+
Run the benchmarks with:
59+
```bash
60+
cargo +nightly bench
61+
```
62+
63+
## End-to-End Example
64+
Let's walk through a full example of using Delphi with the pretrained MiniONN model at `python/minionn/pretrained/relu/model`.
65+
66+
Using Python3.6/7, install the following packages:
67+
```bash
68+
pip install ray[tune]==0.8.0 requests scipy tensorflow==1.15.0
69+
```
70+
Optionally, visualizing results requires the `tensorboard` package:
71+
```bash
72+
pip install tensorboard==1.15.0
73+
```
74+
### Model Preprocessing
75+
For this step we will be working exclusively in the `python/` subdirectory:
76+
```bash
77+
cd python/
78+
```
79+
#### 1. Neural Architecture Search
80+
In order to achieve optimal performance, we need to run NAS on our pretrained model to optimize which activation layers to approximate (see [Delphi paper][delphi] for more details).
81+
82+
Start by running NAS on the total number of activation layers (`-a` flag), in this case 7, with the following command:
83+
```bash
84+
python minionn/minionn_cifar10.py -n 7_layers -d /tmp -a 7 -r minionn/pretrained/relu/model
85+
```
86+
After that has finished, we can review the results by running:
87+
```bash
88+
tensorboard --logdir=/tmp/7_layers
89+
```
90+
and visiting `localhost:6006` in a web browser.
91+
92+
If the resulting networks don't have satisfactory accuracy, rerun the above command with a lower number of activation layers.
93+
94+
#### 2. Serialization
95+
96+
Once a satisfactory network is trained (say at `/tmp/model`), we need to extract the model weights for use in the Rust cryptographic protocol. This can be done by running the following command.
97+
```bash
98+
python extract_keras_weights.py 0 -w /tmp/model -a {approx layers}
99+
```
100+
Where `{approx layers}` is the list of layers being approximated.
101+
102+
This will output a `model.npy` file which is ready to be used by Delphi for secure inference.
103+
104+
Passing the `-q` flag additionally quantizes the model for additional performance, but may lower accuracy. Additionally passing the `-t` flag will test accuracy of the original and quantized network in order for you to decide which is best. Currently, quantizing requires Tensorflow 2.0.
105+
106+
### Performing inference with the model
107+
We will now use this model to perform inference on an image using the code in `rust/experiments/src/inference`:
108+
```bash
109+
cd ../rust/experiments/src/inference
110+
```
111+
Run the following python script to generate a test image:
112+
```bash
113+
python3 generate_test_images.py
114+
```
115+
and perform inference on that image by running:
116+
```bash
117+
cargo +nightly run --release --bin minionn-inference /tmp/model.npy {num of approx layers}
118+
```
119+
120+
## License
121+
122+
Delphi is licensed under either of the following licenses, at your discretion.
123+
124+
* Apache License Version 2.0 ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0)
125+
* MIT license ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT)
126+
127+
Unless you explicitly state otherwise, any contribution submitted for inclusion in Delphi by you shall be dual licensed as above (as defined in the Apache v2 License), without any additional terms or conditions.
128+
129+
[delphi]: https://www.usenix.org/system/files/sec20spring_mishra_prepub.pdf
130+
131+
## Reference paper
132+
133+
[_Delphi: A Cryptographic Inference Service for Neural Networks_][delphi]
134+
[Pratyush Mishra](https://www.github.com/pratyush), [Ryan Lehmkuhl](https://www.github.com/ryanleh), Akshayaram Srinivasan, Wenting Zheng, and Raluca Ada Popa
135+
*Usenix Security Symposium 2020*
136+
137+
## Acknowledgements
138+
139+
This work was supported by:
140+
the National Science Foundation;
141+
and donations from Sloan Foundation, Bakar and Hellman Fellows Fund, Alibaba, Amazon Web Services, Ant Financial, Arm, Capital One, Ericsson, Facebook, Google, Intel, Microsoft, Scotiabank, Splunk and VMware
142+
143+
Some parts of the finite field arithmetic infrastructure in the `algebra` crate have been adapted from code in the [`algebra`](https://github.com/scipr-lab/zexe) crate.
144+
145+
146+

0 commit comments

Comments
 (0)