SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.04017 · 2018

A generic framework for privacy preserving deep learning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1811.04017.json · badge: /api/ran/1811.04017.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Berenice2018/PySyft-Bc community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
SanaAwan5/transfer_learning_on_mnist_spdz community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
numpy_tensor_deserializer Ran
ran on a synthesized input
Berenice2018/PySyft-Bc/syft/serde/torch_serde.py
code served (permissive licence) · get_code("12a7f6850c5c9f29")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy
from tempfile import TemporaryFile

torch.manual_seed(0)

# Create a small numpy array and serialize it to binary format
original_array = numpy.array([[1.0, 2.0, 3.0, 4.0],
                              [5.0, 6.0, 7.0, 8.0]], dtype=numpy.float32)

# Serialize the array to binary format using npy format
temp_file = TemporaryFile()
numpy.save(temp_file, original_array)
temp_file.seek(0)
tensor_bin = temp_file.read()
temp_file.close()

ARGS = {
    "tensor_bin": tensor_bin
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
numpy_tensor_serializer Ran
ran on a synthesized input
Berenice2018/PySyft-Bc/syft/serde/torch_serde.py
code served (permissive licence) · get_code("99998102ce327cf9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bytes. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from tempfile import TemporaryFile

torch.manual_seed(0)

# Create a simple tensor for testing
# Using a small tensor with shape (2, 4) as specified
tensor = torch.randn(2, 4)

ARGS = {
    "tensor": tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
preprocess_data Ran
ran on a synthesized input
SanaAwan5/transfer_learning_on_mnist_spdz/dataset.py
code served (permissive licence) · get_code("ad5eca2af374293a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small synthetic data matching MNIST-like format
# x_train: (batch_size, 28, 28) - grayscale images
# y_train: (batch_size,) - class labels in range [0, 4]

batch_train = 2
batch_test = 3

x_train = np.random.randint(0, 256, size=(batch_train, 28, 28), dtype=np.uint8)
y_train = np.random.randint(0, 5, size=(batch_train,), dtype=np.int64)

x_test = np.random.randint(0, 256, size=(batch_test, 28, 28), dtype=np.uint8)
y_test = np.random.randint(0, 5, size=(batch_test,), dtype=np.int64)

dataset = ((x_train, y_train), (x_test, y_test))

ARGS = {
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
preprocess_data Ran
ran on a synthesized input
SanaAwan5/transfer_learning_on_mnist_spdz/dataset_emnist.py
code served (permissive licence) · get_code("cf1ca8eb225f00e9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from keras.utils import to_categorical

# Create small dummy data matching the expected shapes
# x_train and x_test should be 2D arrays (batch_size, 784) for 28x28 images
# y_train and y_test should be 1D arrays of class labels

batch_train = 2
batch_test = 3
img_pixels = 28 * 28

x_train = np.random.randint(0, 256, size=(batch_train, img_pixels), dtype=np.uint8)
y_train = np.array([0, 5], dtype=np.int32)

x_test = np.random.randint(0, 256, size=(batch_test, img_pixels), dtype=np.uint8)
y_test = np.array([1, 2, 10], dtype=np.int32)

dataset = ((x_train, y_train), (x_test, y_test))

ARGS = {
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
preprocess_data2 Ran
ran on a synthesized input
SanaAwan5/transfer_learning_on_mnist_spdz/dataset_emnist.py
code served (permissive licence) · get_code("5e390dbfdd2a0fd5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small dummy dataset matching MNIST structure
# x_train: (batch_size, 28, 28) - grayscale images
# y_train: (batch_size,) - class labels 0-9
batch_train = 2
batch_test = 3

x_train = np.random.randint(0, 256, size=(batch_train, 28, 28), dtype=np.uint8)
y_train = np.array([0, 1], dtype=np.int32)

x_test = np.random.randint(0, 256, size=(batch_test, 28, 28), dtype=np.uint8)
y_test = np.array([2, 3, 4], dtype=np.int32)

dataset = ((x_train, y_train), (x_test, y_test))

ARGS = {
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
torch_tensor_serializer Ran
ran on a synthesized input
Berenice2018/PySyft-Bc/syft/serde/torch_serde.py
code served (permissive licence) · get_code("806045a2dd946b65")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bytes. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import io

torch.manual_seed(0)

# Create a small tensor to serialize
tensor = torch.randn(2, 4)

ARGS = {
    "tensor": tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differential Privacy do not impact the prediction accuracy, the current implementation of the framework introduces a significant overhead in performance, which will be addressed at a later stage of the development. We believe this work is an important milestone introducing the first reliable, general framework for privacy preserving deep learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1811.04017")
get_code_for_paper("1811.04017")
have("1811.04017")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1811.04017.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1811.04017.svg)](https://syntology.ai/paper/1811.04017)

Connect an agent — have() is free.