SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.19845 · NeurIPS · 2024

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning

Li Liu, Baoyuan Wu, Chao Shen, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Mingli Zhu, Ruotong Wang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 16 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, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 7 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/2407.19845.json · badge: /api/ran/2407.19845.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
sclbd/backdoorbench canonical (classifier label)
classifier basis: census
8 ran · 7 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
add_common_attack_args Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/attack/badnet.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, sclbd/backdoorbench 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.

compute_loss_value Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from SCLBD/BackdoorBench
pointer only; the stored copy get_code serves, from SCLBD/BackdoorBench, is pointer only (licence: NOASSERTION) · get_code("855d4d7e071246f8")
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.

generalize_to_lower_pratio Ran
ran, honoured the contract we drafted
sclbd/backdoorbench/attack/wanet.py
pointer only (licence: NOASSERTION) · get_code("1e9b4bedd9340fe0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

generate_poison Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/generate_by_openattack.py
pointer only (licence: NOASSERTION) · get_code("ecc54476b2581685")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

get_all_data Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/attack_hiddenkiller.py
pointer only (licence: NOASSERTION) · get_code("70493a0d9a933777")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

get_all_data Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/generate_by_openattack.py
pointer only (licence: NOASSERTION) · get_code("68d3f51b067a8c7c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

load_sst2_data Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/backdoorbench_nlp/utils/dataset_loader.py
pointer only (licence: NOASSERTION) · get_code("c92710e81ca322f6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

read_data Ran
ran; our contract draft was wrong, not the code
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/attack_hiddenkiller.py
pointer only (licence: NONE) · get_code("213b3de0b016d2f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sclbd/backdoorbench 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
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/generate_by_openattack.py
pointer only (licence: NOASSERTION) · get_code("a562634d0be51558")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

evaluaion Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/attack_hiddenkiller.py
pointer only (licence: NONE) · get_code("31ff894ab3f7a745")
How it ran

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

gumbel_softmax Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/attack/lws/attack_lws.py
pointer only (licence: NOASSERTION) · get_code("3f472db5c0c14538")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

gumbel_softmax_sample Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/attack/lws/attack_lws.py
pointer only (licence: NOASSERTION) · get_code("1c1c354c8558eb8f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

load_agnews_data Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/utils/dataset_loader.py
pointer only (licence: NOASSERTION) · get_code("f0c1578d10c53cc8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

load_olid_data_taska Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/utils/dataset_loader.py
pointer only (licence: NOASSERTION) · get_code("31ce5e9860be17e4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

mix Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/attack/hiddenkiller/generate_poison_train_data.py
pointer only (licence: NOASSERTION) · get_code("433cf4cd7e583ce3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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.

sample_gumbel Not yet run
unverified (harvested, no recorded run)
sclbd/backdoorbench/backdoorbench_nlp/attack/lws/attack_lws.py
pointer only (licence: NOASSERTION) · get_code("c90c471ae2414cc1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sclbd/backdoorbench (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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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 dated earlier
1708.06733 (2017-08)
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
1905.13409 (2019-05)
Bypassing Backdoor Detection Algorithms in Deep Learning
2206.12654 (2022-06)
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
and 5 more not named here
gumbel_softmax_sample 7 other papers
7 dated earlier
1904.03240 (2019-04)
An Unsupervised Autoregressive Model for Speech Representation Learning
1906.08862 (2019-06)
Neural Stored-program Memory
2005.08392 (2020-05)
Vector-Quantized Autoregressive Predictive Coding
and 4 more not named here
generalize_to_lower_pratio 4 other papers
4 dated earlier
2307.10562 (2023-07)
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
2307.11565 (2023-07)
Adversarial Feature Map Pruning for Backdoor
2310.01875 (2023-10)
Towards Stable Backdoor Purification through Feature Shift Tuning
and 1 more not named here
compute_loss_value 2 other papers
2 dated earlier
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
evaluaion 1 other paper
1 dated earlier
2011.10369 (2020-11)
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
get_all_data 1 other paper
1 dated earlier
2011.10369 (2020-11)
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
gumbel_softmax 1 other paper
1 dated earlier
2106.06361 (2021-06)
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
read_data 1 other paper
1 dated earlier
2011.10369 (2020-11)
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

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

As an emerging approach to explore the vulnerability of deep neural networks (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed successively or concurrently, in the status of a rapid arms race. However, mainly due to the diverse settings, and the difficulties of implementation and reproducibility of existing works, there is a lack of a unified and standardized benchmark of backdoor learning, causing unfair comparisons or unreliable conclusions (e.g., misleading, biased or even false conclusions). Consequently, it is difficult to evaluate the current progress and design the future development roadmap of this literature. To alleviate this dilemma, we build a comprehensive benchmark of backdoor learning called BackdoorBench. Our benchmark makes three valuable contributions to the research community. 1) We provide an integrated implementation of representative backdoor learning algorithms (currently including 20 attack and 32 defense algorithms), based on an extensible modularbased codebase. 2) We conduct comprehensive evaluations with 5 poisoning ratios, based on 4 models and 4 datasets, leading to 11,492 pairs of attack-against-defense evaluations in total. 3) Based on above evaluations, we present abundant analysis from 10 perspectives via 18 useful analysis tools, and provide several inspiring insights about backdoor learning. We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning. Finally, we have created a user-friendly website at http://backdoorbench.com, which collects all important information of BackdoorBench, including the link to Codebase, Docs, Leaderboard, and Model Zoo.

For agents

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

get_harvested_code_for_paper("2407.19845")
get_code_for_paper("2407.19845")
have("2407.19845")

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

curl https://syntology.ai/api/ran/2407.19845.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.19845.svg)](https://syntology.ai/paper/2407.19845)

Connect an agent — have() is free.