SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.05553 · 2020

Differentially private cross-silo federated learning

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 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/2007.05553.json · badge: /api/ran/2007.05553.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
DPBayes/DP-cross-silo-federated-learning canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
generate_proj_matrix Ran
ran; our contract draft was wrong, not the code
DPBayes/DP-cross-silo-federated-learning/utils.py
code served (permissive licence) · get_code("4926b2bd4543e594")
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 torch
import numpy as np
import torch.nn as nn

torch.manual_seed(0)

class MockModel(nn.Module):
    def __init__(self, total_params):
        super().__init__()
        self.total_params = total_params
    
    def forward(self, x):
        return x

# Create a mock model with a specific total_params value
model = MockModel(total_params=20)

# Set up parameters
dim_reduction = 5
dim_red_rng_state = torch.get_rng_state()
proj_const = 2.0
proj_type = 1

ARGS = {
    "model": model,
    "dim_reduction": dim_reduction,
    "dim_red_rng_state": dim_red_rng_state,
    "proj_const": proj_const,
    "proj_type": proj_type
}
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 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
generate_proj_matrix_piece Ran
ran, honoured the contract we drafted
DPBayes/DP-cross-silo-federated-learning/utils.py
code served (permissive licence) · get_code("95860179ce1990cc")
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 (128, 32) 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 as np
import torch.nn as nn

torch.manual_seed(0)

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.total_params = 128
        self.linear = nn.Linear(10, 5)
    
    def forward(self, x):
        return self.linear(x)

model = MockModel()
dim_reduction = 16
max_proj_size = 32
proj_type = 1

ARGS = {
    "model": model,
    "dim_reduction": dim_reduction,
    "max_proj_size": max_proj_size,
    "proj_type": proj_type
}
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 (128, 32) — shape (128, 32) 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
check_for_weights Not yet run
unverified (harvested, no recorded run)
DPBayes/DP-cross-silo-federated-learning/run_client.py
code served (permissive licence) · get_code("5c3c9e248f550907")
How it ran

no invocation recorded.

do_proj_in_steps Not yet run
unverified (harvested, no recorded run)
DPBayes/DP-cross-silo-federated-learning/utils.py
code served (permissive licence) · get_code("960fe2c193bb454d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning to enhance learning and improve security. However, federated learning by itself does not guarantee any privacy for data subjects. To quantify and control how much privacy is compromised in the worst-case, we can use differential privacy. In this paper we combine additively homomorphic secure summation protocols with differential privacy in the so-called cross-silo federated learning setting. The goal is to learn complex models like neural networks while guaranteeing strict privacy for the individual data subjects. We demonstrate that our proposed solutions give prediction accuracy that is comparable to the non-distributed setting, and are fast enough to enable learning models with millions of parameters in a reasonable time. To enable learning under strict privacy guarantees that need privacy amplification by subsampling, we present a general algorithm for oblivious distributed subsampling. However, we also argue that when malicious parties are present, a simple approach using distributed Poisson subsampling gives better privacy. Finally, we show that by leveraging random projections we can further scale-up our approach to larger models while suffering only a modest performance loss.

For agents

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

get_harvested_code_for_paper("2007.05553")
get_code_for_paper("2007.05553")
have("2007.05553")

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

curl https://syntology.ai/api/ran/2007.05553.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.05553.svg)](https://syntology.ai/paper/2007.05553)

Connect an agent — have() is free.