SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.00920 · ICML · 2024

Towards Certified Unlearning for Deep Neural Networks

Tianhao Wang, Binchi Zhang, Jundong Li, Yushun Dong

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 3 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/2408.00920.json · badge: /api/ran/2408.00920.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
zhangbinchi/certified-deep-unlearning canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
grad_batch Ran
ran; our contract draft was wrong, not the code
zhangbinchi/certified-deep-unlearning/unlearn.py
code served (permissive licence) · get_code("58d0cb8a834cbb1b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc1 = nn.Linear(5, 8)
        self.fc2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

model = SimpleModel()

# Create a simple batch loader (list of (data, targets) tuples)
batch_loader = [
    (torch.randn(2, 5), torch.tensor([0, 1])),
    (torch.randn(2, 5), torch.tensor([2, 0]))
]

# Lambda for L2 regularization
lam = 0.01

# Device
device = torch.device('cpu')

ARGS = {
    'batch_loader': batch_loader,
    'lam': lam,
    'model': model,
    'device': device
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
grad_batch_approx Ran
ran; our contract draft was wrong, not the code
zhangbinchi/certified-deep-unlearning/unlearn.py
code served (permissive licence) · get_code("5ab1dbc1b3389dc8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(6, 5)
        self.fc2 = nn.Linear(5, 3)
    
    def forward(self, x):
        x = self.fc1(x)
        x = torch.relu(x)
        x = self.fc2(x)
        return x

model = SimpleModel()

# Create a batch loader (list of (data, targets) tuples)
batch_loader = [
    (torch.randn(2, 6), torch.tensor([0, 1])),
    (torch.randn(2, 6), torch.tensor([2, 0]))
]

# Lambda for L2 regularization
lam = 0.01

# Device
device = torch.device('cpu')

ARGS = {
    'batch_loader': batch_loader,
    'lam': lam,
    'model': model,
    'device': device
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hvp Ran
ran; our contract draft was wrong, not the code
zhangbinchi/certified-deep-unlearning/unlearn.py
code served (permissive licence) · get_code("e261328dc1f89c4a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.autograd import grad

torch.manual_seed(0)

# Create a simple computational graph where y depends on w
# y = sum(w^2) is a simple choice
w = [
    torch.tensor([1.0, 2.0, 3.0, 4.0], requires_grad=True),
    torch.tensor([5.0, 6.0, 7.0, 8.0], requires_grad=True)
]

# Compute y as a scalar that depends on w
y = sum(torch.sum(w_elem ** 2) for w_elem in w)

# Create v with the same structure as w (same length and compatible shapes)
v = [
    torch.tensor([0.1, 0.2, 0.3, 0.4]),
    torch.tensor([0.5, 0.6, 0.7, 0.8])
]

ARGS = {
    'y': y,
    'w': w,
    'v': v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
hvp 1 other paper
1 later
2409.09778 (2024-09)
Rewind-to-Delete: Certified Machine Unlearning for Nonconvex 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

In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees. However, its application to deep neural networks (DNNs), known for their highly nonconvex nature, still poses challenges. To bridge the gap between certified unlearning and DNNs, we propose several simple techniques to extend certified unlearning methods to nonconvex objectives. To reduce the time complexity, we develop an efficient computation method by inverse Hessian approximation without compromising certification guarantees. In addition, we extend our discussion of certification to nonconvergence training and sequential unlearning, considering that real-world users can send unlearning requests at different time points. Extensive experiments on three real-world datasets demonstrate the efficacy of our method and the advantages of certified unlearning in DNNs.

For agents

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

get_harvested_code_for_paper("2408.00920")
get_code_for_paper("2408.00920")
have("2408.00920")

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

curl https://syntology.ai/api/ran/2408.00920.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.00920.svg)](https://syntology.ai/paper/2408.00920)

Connect an agent — have() is free.