SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1708.06733 · 2017

BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures 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/1708.06733.json · badge: /api/ran/1708.06733.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
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
GeorgeTzannetos/badnets reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
aisafety-hkust/backdoor_safety_tuning extension (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
add_common_attack_args Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from retsuh-bqw/fmp
pointer only; the stored copy get_code serves, from retsuh-bqw/fmp, is pointer only (licence: NOASSERTION) · get_code("efd3b8b851a0f5e7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

distillation Ran
ran, violated the contract we drafted
aisafety-hkust/backdoor_safety_tuning/fine_tune/qra.py
pointer only (licence: NOASSERTION) · get_code("5c6b89d763f0a8f3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION). 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.

eval Ran
ran, honoured the contract we drafted
GeorgeTzannetos/badnets/train_eval.py
pointer only (licence: NONE) · get_code("4f825732b3b5e87e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeorgeTzannetos/badnets 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.

extract_list_from_dict Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from DreamtaleCore/Refool
pointer only; the stored copy get_code serves, from DreamtaleCore/Refool, is pointer only (licence: NONE) · get_code("c13ff56b116b021f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_reflection_name Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from DreamtaleCore/Refool
pointer only; the stored copy get_code serves, from DreamtaleCore/Refool, is pointer only (licence: NONE) · get_code("fcd6809bdbf068ea")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

train Ran
ran, honoured the contract we drafted
GeorgeTzannetos/badnets/train_eval.py
pointer only (licence: NONE) · get_code("53377da1ddefc4dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeorgeTzannetos/badnets 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.

add_args Not yet run
unverified (harvested, no recorded run)
aisafety-hkust/backdoor_safety_tuning/fine_tune/ft.py
pointer only (licence: NOASSERTION) · get_code("bf4a97ed98a7136f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION). 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.

add_args Not yet run
unverified (harvested, no recorded run)
aisafety-hkust/backdoor_safety_tuning/fine_tune/qra.py
pointer only (licence: NOASSERTION) · get_code("c8871bb5d53700cc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION). 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 later) and 2 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
add_common_attack_args 8 other papers
8 later
1905.13409 (2019-05)
Bypassing Backdoor Detection Algorithms in Deep Learning
2206.12654 (2022-06)
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
2302.09457 (2023-02)
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
and 5 more not named here
add_args 1 other paper
1 later
1905.13409 (2019-05)
Bypassing Backdoor Detection Algorithms in Deep Learning
add_args 1 other paper
1 later
1905.13409 (2019-05)
Bypassing Backdoor Detection Algorithms in Deep Learning
distillation 1 other paper
1 later
1905.13409 (2019-05)
Bypassing Backdoor Detection Algorithms in Deep Learning
extract_list_from_dict 1 other paper
1 later
2007.02343 (2020-07)
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
get_reflection_name 1 other paper
1 later
2007.02343 (2020-07)
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

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

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on many GPUs; as a result, many users outsource the training procedure to the cloud or rely on pre-trained models that are then fine-tuned for a specific task. In this paper we show that outsourced training introduces new security risks: an adversary can create a maliciously trained network (a backdoored neural network, or a \emph{BadNet}) that has state-of-the-art performance on the user's training and validation samples, but behaves badly on specific attacker-chosen inputs. We first explore the properties of BadNets in a toy example, by creating a backdoored handwritten digit classifier. Next, we demonstrate backdoors in a more realistic scenario by creating a U.S. street sign classifier that identifies stop signs as speed limits when a special sticker is added to the stop sign; we then show in addition that the backdoor in our US street sign detector can persist even if the network is later retrained for another task and cause a drop in accuracy of {25}\% on average when the backdoor trigger is present. These results demonstrate that backdoors in neural networks are both powerful and---because the behavior of neural networks is difficult to explicate---stealthy. This work provides motivation for further research into techniques for verifying and inspecting neural networks, just as we have developed tools for verifying and debugging software.

For agents

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

get_harvested_code_for_paper("1708.06733")
get_code_for_paper("1708.06733")
have("1708.06733")

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

curl https://syntology.ai/api/ran/1708.06733.json

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

[![Syntology run record](https://syntology.ai/api/ran/1708.06733.svg)](https://syntology.ai/paper/1708.06733)

Connect an agent — have() is free.