SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.08970 · NeurIPS · 2022

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

Micah Goldblum, Liam Fowl, Tom Goldstein, Rama Chellappa, Hossein Souri

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 2 no recorded run), measured 2026-11-21; 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/2106.08970.json · badge: /api/ran/2106.08970.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
hsouri/Sleeper-Agent canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
bypass_last_layer Ran
ran; our contract draft was wrong, not the code
hsouri/Sleeper-Agent/forest/victims/batched_attacks.py
pointer only (licence: NONE) · get_code("4f1b22f771a50e6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsouri/Sleeper-Agent 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.

BaseAttack Not yet run
unverified (harvested, no recorded run)
hsouri/Sleeper-Agent/forest/victims/batched_attacks.py
pointer only (licence: NONE) · get_code("34911817e88e224a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsouri/Sleeper-Agent 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.

HTBD Not yet run
unverified (harvested, no recorded run)
hsouri/Sleeper-Agent/forest/victims/batched_attacks.py
pointer only (licence: NONE) · get_code("5d42b7b133f5db30")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsouri/Sleeper-Agent 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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 2026-11-21.

Repositories linked to this paper

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

Abstract

As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This vulnerability is then activated at inference time by placing a "trigger" into the model's input. Typical backdoor attacks insert the trigger directly into the training data, although the presence of such an attack may be visible upon inspection. In contrast, the Hidden Trigger Backdoor Attack achieves poisoning without placing a trigger into the training data at all. However, this hidden trigger attack is ineffective at poisoning neural networks trained from scratch. We develop a new hidden trigger attack, Sleeper Agent, which employs gradient matching, data selection, and target model re-training during the crafting process. Sleeper Agent is the first hidden trigger backdoor attack to be effective against neural networks trained from scratch. We demonstrate its effectiveness on ImageNet and in black-box settings. Our implementation code can be found at: https://github.com/hsouri/Sleeper-Agent.

For agents

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

get_harvested_code_for_paper("2106.08970")
get_code_for_paper("2106.08970")
have("2106.08970")

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

curl https://syntology.ai/api/ran/2106.08970.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.08970.svg)](https://syntology.ai/paper/2106.08970)

Connect an agent — have() is free.