SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.14956 · 2020

Generating Natural Language Attacks in a Hard Label Black Box Setting

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 5 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2012.14956.json · badge: /api/ran/2012.14956.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
RishabhMaheshwary/hard-label-attack canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
zhuhai-ustc/limeattack reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_sim Ran
ran, honoured the contract we drafted
RishabhMaheshwary/hard-label-attack/classification_attack.py
pointer only (licence: NONE) · get_code("c21e48ffeb28f27c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RishabhMaheshwary/hard-label-attack 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_attack_result Ran
ran; our contract draft was wrong, not the code
RishabhMaheshwary/hard-label-attack/classification_attack.py
pointer only (licence: NONE) · get_code("42fd8b8cd0d91749")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RishabhMaheshwary/hard-label-attack 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_obj Ran
ran; our contract draft was wrong, not the code
zhuhai-ustc/limeattack/LimeAttack_classification.py
pointer only (licence: NONE) · get_code("b91a5961fb87cb5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhuhai-ustc/limeattack 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.

pick_most_similar_words_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RishabhMaheshwary/hard-label-attack/classification_attack.py
pointer only (licence: NONE) · get_code("87b2750a51e1c3e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RishabhMaheshwary/hard-label-attack 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.

read_data Ran
ran; our contract draft was wrong, not the code
RishabhMaheshwary/hard-label-attack/nli_attack.py
pointer only (licence: NONE) · get_code("cee2b1928c7dcb6a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RishabhMaheshwary/hard-label-attack 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.

split_token Ran
ran; our contract draft was wrong, not the code
zhuhai-ustc/limeattack/LimeAttack_classification.py
pointer only (licence: NONE) · get_code("8d7dd0e725cac033")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhuhai-ustc/limeattack 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 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
load_obj 6 other papers
4 dated earlier, 2 later
1608.02214 (2016-08)
Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network
1810.03642 (2018-10)
Fast Context Adaptation via Meta-Learning
1902.11020 (2019-02)
DPOD: 6D Pose Object Detector and Refiner
and 3 more not named here
pick_most_similar_words_batch 2 other papers
2 dated earlier
1907.11932 (2019-07)
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
2004.09984 (2020-04)
BERT-ATTACK: Adversarial Attack Against BERT Using BERT
read_data 1 other paper
1 dated earlier
1907.11932 (2019-07)
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

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

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification and entailment tasks. Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model. At each iteration, the optimization procedure allow word replacements that maximizes the overall semantic similarity between the original and the adversarial text. Further, our approach does not rely on using substitute models or any kind of training data. We demonstrate the efficacy of our proposed approach through extensive experimentation and ablation studies on five state-of-the-art target models across seven benchmark datasets. In comparison to attacks proposed in prior literature, we are able to achieve a higher success rate with lower word perturbation percentage that too in a highly restricted setting.

For agents

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

get_harvested_code_for_paper("2012.14956")
get_code_for_paper("2012.14956")
have("2012.14956")

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

curl https://syntology.ai/api/ran/2012.14956.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.14956.svg)](https://syntology.ai/paper/2012.14956)

Connect an agent — have() is free.