SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.08504 · ICLR · 2022

Label Leakage and Protection in Two-party Split Learning

Virginia Smith, Xin Yang, Oscar Li, Jiankai Sun, Weihao Gao, Hongyi Zhang, Junyuan Xie, Chong Wang

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/2102.08504.json · badge: /api/ran/2102.08504.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
Koukyosyumei/AIJack community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
attach_normattack_to_splitnn Ran
ran; our contract draft was wrong, not the code
Koukyosyumei/AIJack/src/aijack/attack/labelleakage/normattack.py
code served (permissive licence) · get_code("e1b8d70923b7960e")
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 type. 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
from torch.nn import functional as F

torch.manual_seed(0)

# Build a minimal SplitNN base class that satisfies the function's usage
class MinimalSplitNN(nn.Module):
    def __init__(self, input_dim=4, output_dim=2):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
        self.clients = [MinimalClient()]
        
    def forward(self, x):
        return self.linear(x)
    
    def backward_gradient(self, grad):
        # Simulate backward pass
        pass

class MinimalClient(nn.Module):
    def __init__(self):
        super().__init__()
        self.grad_from_next_client = None
    
    def set_grad(self, grad):
        self.grad_from_next_client = grad

# Create a minimal attack criterion (loss function)
attack_criterion = nn.CrossEntropyLoss()

# Create a minimal dataloader (list of (inputs, labels) tuples)
dataloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([1, 0])),
]

# Patch the SplitNN to work with the attack
class PatchedSplitNN(MinimalSplitNN):
    def forward(self, x):
        output = self.linear(x)
        # Store output for gradient extraction
        output.grad = torch.randn(2, 2)  # Mock gradient
        # Set client gradient
        self.clients[0].grad_from_next_client = torch.randn(2, 4)
        return output

ARGS = {
    'cls': PatchedSplitNN,
    'attack_criterion': attack_criterion,
    'target_client_index': 0,
    'device': 'cpu',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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

Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the private label information from the other party during split training, and whether there are methods that can protect against such attacks. Specifically, we first formulate a realistic threat model and propose a privacy loss metric to quantify label leakage in split learning. We then show that there exist two simple yet effective methods within the threat model that can allow one party to accurately recover private ground-truth labels owned by the other party. To combat these attacks, we propose several random perturbation techniques, including Marvell, an approach that strategically finds the structure of the noise perturbation by minimizing the amount of label leakage (measured through our quantification metric) of a worst-case adversary. We empirically demonstrate the effectiveness of our protection techniques against the identified attacks, and show that Marvell in particular has improved privacy-utility tradeoffs relative to baseline approaches.

For agents

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

get_harvested_code_for_paper("2102.08504")
get_code_for_paper("2102.08504")
have("2102.08504")

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

curl https://syntology.ai/api/ran/2102.08504.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.08504.svg)](https://syntology.ai/paper/2102.08504)

Connect an agent — have() is free.