SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.12005 · ICLR · 2023

Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors

Xiaolin Huang, Yanzhi Wang, Minghai Qin, Geng Yuan, Yifan Gong, Sizhe Chen, Xinwen Cheng

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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; 2 failures of our instrument; 4 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/2211.12005.json · badge: /api/ran/2211.12005.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
sizhe-chen/sep canonical (classifier label)
classifier basis: classifier_2025
2 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_correct Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sizhe-chen/sep/ens.py
pointer only (licence: NONE) · get_code("098344b3a1ff9bea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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.

get_dataloader Ran
ran; our contract draft was wrong, not the code
sizhe-chen/sep/vanilla.py
pointer only (licence: NONE) · get_code("2f4a2990cb7bdbd1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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.

get_dataloader Not yet run
unverified (harvested, no recorded run)
sizhe-chen/sep/ens.py
pointer only (licence: NONE) · get_code("e246a0e4d92b7f70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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.

get_mean_feature Not yet run
unverified (harvested, no recorded run)
sizhe-chen/sep/ens_feature.py
pointer only (licence: NONE) · get_code("7c2ff343d57dd678")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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.

valid_test Not yet run
unverified (harvested, no recorded run)
sizhe-chen/sep/ens.py
pointer only (licence: NONE) · get_code("003d8a66eb7cb80b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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.

valid_test Not yet run
unverified (harvested, no recorded run)
sizhe-chen/sep/vanilla.py
pointer only (licence: NONE) · get_code("a58c8d3462fec315")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/sep 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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 data becomes increasingly vital, a company would be very cautious about releasing data, because the competitors could use it to train high-performance models, thereby posing a tremendous threat to the company's commercial competence. To prevent training good models on the data, we could add imperceptible perturbations to it. Since such perturbations aim at hurting the entire training process, they should reflect the vulnerability of DNN training, rather than that of a single model. Based on this new idea, we seek perturbed examples that are always unrecognized (never correctly classified) in training. In this paper, we uncover them by model checkpoints' gradients, forming the proposed self-ensemble protection (SEP), which is very effective because (1) learning on examples ignored during normal training tends to yield DNNs ignoring normal examples; (2) checkpoints' cross-model gradients are close to orthogonal, meaning that they are as diverse as DNNs with different architectures. That is, our amazing performance of ensemble only requires the computation of training one model. By extensive experiments with 9 baselines on 3 datasets and 5 architectures, SEP is verified to be a new state-of-the-art, e.g., our small ∞ = 2/255 perturbations reduce the accuracy of a CIFAR-10 ResNet18 from 94.56% to 14.68%, compared to 41.35% by the best-known method. Code is available at https://github.com/Sizhe-Chen/SEP. Can we use these intermediate checkpoint models for data protection in a self-ensemble manner?

For agents

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

get_harvested_code_for_paper("2211.12005")
get_code_for_paper("2211.12005")
have("2211.12005")

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

curl https://syntology.ai/api/ran/2211.12005.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.12005.svg)](https://syntology.ai/paper/2211.12005)

Connect an agent — have() is free.