SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03233 · 2024

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2404.03233.json · badge: /api/ran/2404.03233.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
tasi-lab/unlearning-inversion-attacks canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
activation_errors Ran
ran; our contract draft was wrong, not the code
tasi-lab/unlearning-inversion-attacks/recovery/metrics.py
pointer only (licence: NONE) · get_code("e551d62ffffcfda9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

densenet_cifar Ran
ran; our contract draft was wrong, not the code
tasi-lab/unlearning-inversion-attacks/recovery/nn/densenet.py
pointer only (licence: NONE) · get_code("7db01b64f42f28ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

make_dict Ran
ran; our contract draft was wrong, not the code
tasi-lab/unlearning-inversion-attacks/label_inference.py
pointer only (licence: NONE) · get_code("a3ca28dee046906c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

psnr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tasi-lab/unlearning-inversion-attacks/recovery/metrics.py
pointer only (licence: NONE) · get_code("5ef2f520281c0bdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

reconstruction_costs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tasi-lab/unlearning-inversion-attacks/recovery/recovery_algo.py
pointer only (licence: NONE) · get_code("d696213f6c2f41c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

total_variation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tasi-lab/unlearning-inversion-attacks/recovery/metrics.py
pointer only (licence: NONE) · get_code("3d23162c75564e01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

construct_dataloaders Not yet run
unverified (harvested, no recorded run)
tasi-lab/unlearning-inversion-attacks/recovery/data_processing.py
pointer only (licence: NONE) · get_code("3c356eac4f901289")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

construct_model Not yet run
unverified (harvested, no recorded run)
tasi-lab/unlearning-inversion-attacks/recovery/nn/models.py
pointer only (licence: NONE) · get_code("755e669a609b810f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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.

new_plot Not yet run
unverified (harvested, no recorded run)
tasi-lab/unlearning-inversion-attacks/recovery_data.py
pointer only (licence: NONE) · get_code("caf7ebba1cdf55d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tasi-lab/unlearning-inversion-attacks 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 3 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
activation_errors 5 other papers
4 dated earlier, 1 later
Sun_Soteria_Provable_Defense_Against_Privacy_Leakage_in_Federated_Learning_From_CVPR_2021_paper (2021 (year only))
Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
2107.01154 (2021-07)
Gradient-Leakage Resilient Federated Learning
2308.04699 (2023-08)
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
and 2 more not named here
psnr 5 other papers
4 dated earlier, 1 later
Sun_Soteria_Provable_Defense_Against_Privacy_Leakage_in_Federated_Learning_From_CVPR_2021_paper (2021 (year only))
Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
2107.01154 (2021-07)
Gradient-Leakage Resilient Federated Learning
2308.04699 (2023-08)
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
and 2 more not named here
total_variation 5 other papers
4 dated earlier, 1 later
Sun_Soteria_Provable_Defense_Against_Privacy_Leakage_in_Federated_Learning_From_CVPR_2021_paper (2021 (year only))
Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
2107.01154 (2021-07)
Gradient-Leakage Resilient Federated Learning
2308.04699 (2023-08)
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
and 2 more not named here
densenet_cifar 4 other papers
4 dated earlier
2107.01154 (2021-07)
Gradient-Leakage Resilient Federated Learning
Zhang_Generative_Gradient_Inversion_via_Over-Parameterized_Networks_in_Federated_Learning_ICCV_2023_paper (2023 (year only))
Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning
2308.04699 (2023-08)
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
and 1 more not named here
reconstruction_costs 2 other papers
2 dated earlier
2003.14053 (2020-03)
Inverting Gradients -- How easy is it to break privacy in federated learning?
2309.13016 (2023-09)
Understanding Deep Gradient Leakage via Inversion Influence Functions

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

Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning mainly focus on the efficacy and efficiency of unlearning methods, while neglecting the investigation of the privacy vulnerability during the unlearning process. With two versions of a model available to an adversary, that is, the original model and the unlearned model, machine unlearning opens up a new attack surface. In this paper, we conduct the first investigation to understand the extent to which machine unlearning can leak the confidential content of the unlearned data. Specifically, under the Machine Learning as a Service setting, we propose unlearning inversion attacks that can reveal the feature and label information of an unlearned sample by only accessing the original and unlearned model. The effectiveness of the proposed unlearning inversion attacks is evaluated through extensive experiments on benchmark datasets across various model architectures and on both exact and approximate representative unlearning approaches. The experimental results indicate that the proposed attack can reveal the sensitive information of the unlearned data. As such, we identify three possible defenses that help to mitigate the proposed attacks, while at the cost of reducing the utility of the unlearned model. The study in this paper uncovers an underexplored gap between machine unlearning and the privacy of unlearned data, highlighting the need for the careful design of mechanisms for implementing unlearning without leaking the information of the unlearned data.

For agents

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

get_harvested_code_for_paper("2404.03233")
get_code_for_paper("2404.03233")
have("2404.03233")

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

curl https://syntology.ai/api/ran/2404.03233.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.03233.svg)](https://syntology.ai/paper/2404.03233)

Connect an agent — have() is free.