SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.02462 · 2024

A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure 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/2404.02462.json · badge: /api/ran/2404.02462.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
jiepku/partcrop canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
load_checkpoints Ran
ran; our contract draft was wrong, not the code
jiepku/partcrop/mia_test.py
code served (permissive licence) · get_code("884de89425e4981f")
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 MinimalAttacker. 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 os
import torch
import torch.nn as nn
import tempfile

torch.manual_seed(0)

# Create a temporary directory for output
temp_dir = tempfile.mkdtemp()

# Create a minimal attacker model
class MinimalAttacker(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create an attacker instance
attacker = MinimalAttacker()

# Create a checkpoint file with the expected structure
checkpoint = {
    'net': attacker.state_dict()
}

# Save the checkpoint
save_name = 'test_checkpoint.pt'
checkpoint_path = os.path.join(temp_dir, save_name)
torch.save(checkpoint, checkpoint_path)

# Create args object with output_dir attribute
class Args:
    def __init__(self, output_dir):
        self.output_dir = output_dir

args = Args(temp_dir)

ARGS = {
    'args': args,
    'attacker': attacker,
    'save_name': save_name
}
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 MinimalAttacker — a MinimalAttacker output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalAttacker output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also confronts significant privacy concerns, especially in vision. In this paper, we aim to perform membership inference on visual self-supervised models in a more realistic setting: self-supervised training method and details are unknown for an adversary when attacking as he usually faces a black-box system in practice. In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e.g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop. It is motivated by the shared part-aware capability among models and stronger part response on the training data. Specifically, PartCrop crops parts of objects in an image to query responses with the image in representation space. We conduct extensive attacks on self-supervised models with different training protocols and structures using three widely used image datasets. The results verify the effectiveness and generalization of PartCrop. Moreover, to defend against PartCrop, we evaluate two common approaches, i.e., early stop and differential privacy, and propose a tailored method called shrinking crop scale range. The defense experiments indicate that all of them are effective. Our code is available at https://github.com/JiePKU/PartCrop.

For agents

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

get_harvested_code_for_paper("2404.02462")
get_code_for_paper("2404.02462")
have("2404.02462")

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

curl https://syntology.ai/api/ran/2404.02462.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.02462.svg)](https://syntology.ai/paper/2404.02462)

Connect an agent — have() is free.