SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.11565 · ICLR · 2024

Adversarial Feature Map Pruning for Backdoor

Dong Huang, Qingwen Bu

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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, 2 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2307.11565.json · badge: /api/ran/2307.11565.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
retsuh-bqw/FMP canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
retsuh-bqw/fmp canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
ase2023paper/fmt marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
PreActResNet18 Ran
ran; our contract draft was wrong, not the code
retsuh-bqw/FMP/models/preact_resnet.py
pointer only (licence: NONE); the stored copy get_code serves, from szegedai/SemanticBackdoorDetection, is pointer only (licence: NONE) · get_code("a55348359ff9d8f1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, retsuh-bqw/FMP 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_common_attack_args Ran
ran; our contract draft was wrong, not the code
retsuh-bqw/fmp/attack/badnet.py
pointer only (licence: NOASSERTION) · get_code("efd3b8b851a0f5e7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, retsuh-bqw/fmp (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.

dynamiccluster Ran
ran, violated the contract we drafted
retsuh-bqw/fmp/defense/fgsm-feature.py
pointer only (licence: NOASSERTION) · get_code("450c80c1f2967167")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, retsuh-bqw/fmp (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.

generalize_to_lower_pratio Ran
ran, honoured the contract we drafted
retsuh-bqw/FMP/attack/wanet.py
pointer only (licence: NONE); the stored copy get_code serves, from sclbd/backdoorbench, is pointer only (licence: NOASSERTION) · get_code("1e9b4bedd9340fe0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, retsuh-bqw/FMP 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.

initialize Ran
ran; our contract draft was wrong, not the code
ase2023paper/fmt/defense/feature.py
pointer only (licence: NOASSERTION) · get_code("ee4996a2c442fcea")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ase2023paper/fmt (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.

is_valid_file Ran
ran, violated the contract we drafted
retsuh-bqw/FMP/for_imagenet/generate_poison_val_badnet.py
pointer only (licence: NONE); the stored copy get_code serves, from shawkui/Proactive_Defensive_Backdoor, is pointer only (licence: NOASSERTION) · get_code("ea3c60ddf40d46bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, retsuh-bqw/FMP 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.

ranking Ran
ran; our contract draft was wrong, not the code
retsuh-bqw/fmp/defense/fgsm-feature.py
pointer only (licence: NOASSERTION) · get_code("d01e01e22a12d3dc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, retsuh-bqw/fmp (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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 4 the same month, 4 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
PreActResNet18 22 other papers
11 dated earlier, 1 the same month, 9 later, 1 same year, order not determinable
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
2003.04887 (2020-03)
ReZero is All You Need: Fast Convergence at Large Depth
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 19 more not named here
add_common_attack_args 8 other papers
4 dated earlier, 1 the same month, 3 later
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
generalize_to_lower_pratio 4 other papers
1 the same month, 3 later
2307.10562 (2023-07)
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
2310.01875 (2023-10)
Towards Stable Backdoor Purification through Feature Shift Tuning
2405.16112 (2024-05)
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
and 1 more not named here
is_valid_file 3 other papers
1 the same month, 2 later
2307.10562 (2023-07)
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
2310.01875 (2023-10)
Towards Stable Backdoor Purification through Feature Shift Tuning
2405.16112 (2024-05)
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor

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 neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to specific training data. Existing defense strategies primarily focus on using reverse engineering to reproduce the backdoor trigger generated by attackers and subsequently repair the DNN model by adding the trigger into inputs and fine-tuning the model with ground-truth labels. However, once the trigger generated by the attackers is complex and invisible, the defender cannot reproduce the trigger successfully then the DNN model will not be repaired, as the trigger is not effectively removed. In this work, we propose Adversarial Feature Map Pruning for Backdoor (FMP) to mitigate backdoor from the DNN. Unlike existing defense strategies, which focus on reproducing backdoor triggers, FMP attempts to prune backdoor feature maps, which are trained to extract backdoor information from inputs. After pruning these backdoor feature maps, FMP will fine-tune the model with a secure subset of training data. Our experiments demonstrate that, compared to existing defense strategies, FMP can effectively reduce the Attack Success Rate (ASR) even against the most complex and invisible attack triggers (e.g., FMP decreases the ASR to 2.86% in CIFAR10, which is 19.2% to 65.41% lower than baselines). Second, unlike conventional defense methods that tend to exhibit low robust accuracy (that is, the accuracy of the model on poisoned data), FMP achieves a higher RA, indicating its superiority in maintaining model performance while mitigating the effects of backdoor attacks (e.g., FMP obtains 87.40% RA in CIFAR10). Our code is publicly available at: https://github.com/retsuh-bqw/FMP.

For agents

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

get_harvested_code_for_paper("2307.11565")
get_code_for_paper("2307.11565")
have("2307.11565")

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

curl https://syntology.ai/api/ran/2307.11565.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.11565.svg)](https://syntology.ai/paper/2307.11565)

Connect an agent — have() is free.