SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.06156 · 2019

A Little Is Enough: Circumventing Defenses For Distributed Learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/1902.06156.json · badge: /api/ran/1902.06156.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
kkonstantinidis/ByzShield reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
add_fit_args Ran
ran; our contract draft was wrong, not the code
kkonstantinidis/ByzShield/src/distributed_evaluator.py
pointer only (licence: NONE) · get_code("ad4da1db77b0c2a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kkonstantinidis/ByzShield when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
kkonstantinidis/ByzShield/src/distributed_evaluator.py
pointer only (licence: NONE) · get_code("4d3faaaa1c706b0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kkonstantinidis/ByzShield when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
accuracy 23 other papers
7 dated earlier, 16 later
1603.07285 (2016-03)
A guide to convolution arithmetic for deep learning
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1608.08710 (2016-08)
Pruning Filters for Efficient ConvNets
and 20 more not named here
add_fit_args 1 other paper
1 later
2010.04902 (2020-10)
ByzShield: An Efficient and Robust System for Distributed Training

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

Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their corresponding defenses assume that the rogue participants are (a) omniscient (know the data of all other participants), and (b) introduce large change to the parameters. We show that small but well-crafted changes are sufficient, leading to a novel non-omniscient attack on distributed learning that go undetected by all existing defenses. We demonstrate our attack method works not only for preventing convergence but also for repurposing of the model behavior (backdooring). We show that 20% of corrupt workers are sufficient to degrade a CIFAR10 model accuracy by 50%, as well as to introduce backdoors into MNIST and CIFAR10 models without hurting their accuracy

For agents

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

get_harvested_code_for_paper("1902.06156")
get_code_for_paper("1902.06156")
have("1902.06156")

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

curl https://syntology.ai/api/ran/1902.06156.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.06156.svg)](https://syntology.ai/paper/1902.06156)

Connect an agent — have() is free.