SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.17826 · ACL · 2023

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

Yang Zhang, Zheng Li, Shiqing Ma, Kai Mei, Zhenting Wang

arXiv · PDF · Open in the Atlas

Code that ran

16 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 5 have no contract verdict; 8 failures of our instrument; 4 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/2305.17826.json · badge: /api/ran/2305.17826.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
ru-system-software-and-security/notable canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
RU-System-Software-and-Security/Notable community
Papers with Code archive
14 ran · 4 no recorded run
FunctionStatusWhere it lives
AccuracyFn Ran
ran on a synthesized input · constructed an object; no result was computed
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("03ba856c8d50cb92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

Collator Ran
ran on a synthesized input · constructed an object; no result was computed
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("736b1e3d7a04f0c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

GradientStorage Ran
ran on a synthesized input · constructed an object; no result was computed
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("3109240945514efb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

PredictWrapper Ran
ran on a synthesized input · constructed an object; no result was computed
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("b7a8ca735d37a6af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

TriggerTemplatizer Ran
ran on a synthesized input · constructed an object; no result was computed
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("44c86571efd62a1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

encode_label Ran
ran, honoured the contract we drafted
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("d174dc1e0823ae67")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

get_embeddings Ran
ran; our contract draft was wrong, not the code
ru-system-software-and-security/notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("20a9293a820f617d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ru-system-software-and-security/notable 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.

get_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("f614f524884546fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

hotflip_attack Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ru-system-software-and-security/notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("309e71f4157403d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ru-system-software-and-security/notable 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.

isupper Ran
ran, violated the contract we drafted
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("6a57ad8e1ebd28ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

load_augmented_trigger_dataset Ran
ran; our contract draft was wrong, not the code
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("167ee534ecb844a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

load_jsonl Ran
ran; our contract draft was wrong, not the code
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("3193029e7175ef98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

load_trigger_dataset Ran
ran; our contract draft was wrong, not the code
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("8291054ef431334e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

load_tsv Ran
ran; our contract draft was wrong, not the code
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("e284d68f65c1afe4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

pad_squeeze_sequence Ran
ran, honoured the contract we drafted
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("d133860668e93507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

replace_trigger_tokens Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("ec5d1f66dd9187f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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_task_specific_tokens Not yet run
unverified (harvested, no recorded run)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("02ee33f23a8f0591")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

load_pretrained Not yet run
unverified (harvested, no recorded run)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("a5946a0ceaabfe6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

run_model Not yet run
unverified (harvested, no recorded run)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("4ef0bced0d8f70ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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.

set_seed Not yet run
unverified (harvested, no recorded run)
RU-System-Software-and-Security/Notable/autoprompt/create_trigger.py
pointer only (licence: NONE) · get_code("52e446206cdc2fa5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RU-System-Software-and-Security/Notable 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 17 are also present in other papers whose code we hold (17 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
hotflip_attack
brick of this paper's assembly: update_rule
4 other papers
2 dated earlier, 2 later · 1 only as an assembly brick
2010.15980 (2020-10)
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
2310.19156 (2023-10)
Poisoning Retrieval Corpora by Injecting Adversarial Passages
and 1 more not named here
get_embeddings
brick of this paper's assembly: model
2 other papers
2 dated earlier · 1 only as an assembly brick
2010.15980 (2020-10)
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
AccuracyFn
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
Collator
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
GradientStorage
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
add_task_specific_tokens
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
encode_label
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
get_loss
brick of this paper's assembly: loss
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
isupper
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
load_augmented_trigger_dataset
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
load_jsonl
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
load_pretrained
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
load_tsv
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
pad_squeeze_sequence
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
replace_trigger_tokens
brick of this paper's assembly: data_transform
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
run_model
brick of this paper's assembly: entry
1 other paper
1 dated earlier
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning
set_seed
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01751 (2021-06)
Reordering Examples Helps during Priming-based Few-Shot Learning

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

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks. In this work, we propose transferable backdoor attacks against prompt-based models, called NOTABLE, which is independent of downstream tasks and prompting strategies. Specifically, NOTABLE injects backdoors into the encoders of PLMs by utilizing an adaptive verbalizer to bind triggers to specific words (i.e., anchors). It activates the backdoor by pasting input with triggers to reach adversary-desired anchors, achieving independence from downstream tasks and prompting strategies. We conduct experiments on six NLP tasks, three popular models, and three prompting strategies. Empirical results show that NOTABLE achieves superior attack performance (i.e., attack success rate over 90% on all the datasets), and outperforms two state-ofthe-art baselines. Evaluations on three defenses show the robustness of NOTABLE. Our code can be found at https://github.com/RU-System-Software-and-Security/Notable.

For agents

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

get_harvested_code_for_paper("2305.17826")
get_code_for_paper("2305.17826")
have("2305.17826")

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

curl https://syntology.ai/api/ran/2305.17826.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.17826.svg)](https://syntology.ai/paper/2305.17826)

Connect an agent — have() is free.