SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.09173 · 2024

Potion: Towards Poison Unlearning

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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 1 has no contract verdict; 5 failures of our instrument; 3 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/2406.09173.json · badge: /api/ran/2406.09173.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
if-loops/towards_poison_unlearning canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_accuracy Ran
ran, honoured the contract we drafted
if-loops/towards_poison_unlearning/visualize.py
pointer only (licence: GPL-3.0) · get_code("1808b5d76587f897")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

conv_bn Ran
ran; our contract draft was wrong, not the code
if-loops/towards_poison_unlearning/src/resnet.py
pointer only (licence: GPL-3.0) · get_code("4844d5c6ef2edff8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

convert_boolean_to_int Ran
ran; our contract draft was wrong, not the code
if-loops/towards_poison_unlearning/src/utils.py
pointer only (licence: GPL-3.0) · get_code("f83c8e9c6bd4eaf8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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_custom_dataset Ran
ran; our contract draft was wrong, not the code
if-loops/towards_poison_unlearning/src/utils.py
pointer only (licence: GPL-3.0) · get_code("e01e044ea7191062")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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_labels Ran
ran on a synthesized input
if-loops/towards_poison_unlearning/src/datasets.py
pointer only (licence: GPL-3.0) · get_code("bf20b453f51520be")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

parse_pretrain_dirname Ran
ran; our contract draft was wrong, not the code
if-loops/towards_poison_unlearning/visualize.py
pointer only (licence: GPL-3.0) · get_code("f69494457c839f5f")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

parse_unlearn_dirname Ran
ran; our contract draft was wrong, not the code
if-loops/towards_poison_unlearning/visualize.py
pointer only (licence: GPL-3.0) · get_code("14698f649f4374cd")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

define_model Not yet run
unverified (harvested, no recorded run)
if-loops/towards_poison_unlearning/src/utils.py
pointer only (licence: GPL-3.0) · get_code("6e7f7f4554385493")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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.

get_features Not yet run
unverified (harvested, no recorded run)
if-loops/towards_poison_unlearning/src/analyze_feats.py
pointer only (licence: GPL-3.0) · get_code("d17fd04d5d7ea7a0")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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_dataset Not yet run
unverified (harvested, no recorded run)
if-loops/towards_poison_unlearning/src/datasets.py
pointer only (licence: GPL-3.0) · get_code("74929642bc9b52f8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, if-loops/towards_poison_unlearning, is not in the permissive set Syntology serves inline. 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
compute_accuracy 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning
conv_bn 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning
get_features 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning
get_labels 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning
load_dataset 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning
parse_pretrain_dirname 1 other paper
1 dated earlier
2402.14015 (2024-02)
Corrective Machine Unlearning

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

Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the poisoned data can be identified. This necessitates the development of methods to remove, i.e. unlearn, poison triggers from already trained models with only a subset of the poison data available. The requirements for this task significantly deviate from privacy-focused unlearning where all of the data to be forgotten by the model is known. Previous work has shown that the undiscovered poisoned samples lead to a failure of established unlearning methods, with only one method, Selective Synaptic Dampening (SSD), showing limited success. Even full retraining, after the removal of the identified poison, cannot address this challenge as the undiscovered poison samples lead to a reintroduction of the poison trigger in the model. Our work addresses two key challenges to advance the state of the art in poison unlearning. First, we introduce a novel outlier-resistant method, based on SSD, that significantly improves model protection and unlearning performance. Second, we introduce Poison Trigger Neutralisation (PTN) search, a fast, parallelisable, hyperparameter search that utilises the characteristic "unlearning versus model protection" trade-off to find suitable hyperparameters in settings where the forget set size is unknown and the retain set is contaminated. We benchmark our contributions using ResNet-9 on CIFAR10 and WideResNet-28x10 on CIFAR100. Experimental results show that our method heals 93.72% of poison compared to SSD with 83.41% and full retraining with 40.68%. We achieve this while also lowering the average model accuracy drop caused by unlearning from 5.68% (SSD) to 1.41% (ours).

For agents

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

get_harvested_code_for_paper("2406.09173")
get_code_for_paper("2406.09173")
have("2406.09173")

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

curl https://syntology.ai/api/ran/2406.09173.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.09173.svg)](https://syntology.ai/paper/2406.09173)

Connect an agent — have() is free.