SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05453 · ICML · 2024

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Lei Feng, Hongxin Wei, Huiping Zhuang, Xiaofeng Cao, Zhenlong Liu

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 11 failures of our instrument; 1 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/2402.05453.json · badge: /api/ran/2402.05453.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
ml-stat-Sustech/ConvexConcaveLoss canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
ml-stat-sustech/convexconcaveloss canonical (classifier label)
classifier basis: classifier_2025
6 ran · 0 no recorded run
FunctionStatusWhere it lives
CCEL Ran
ran on a synthesized input
ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py
pointer only (licence: NONE) · get_code("44dc0ab35e0ce208")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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.

call_function_from_module Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/utils.py
pointer only (licence: NONE) · get_code("aa4d7b77f7ce2a82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

ce_concave_exp_loss Ran
ran; our contract draft was wrong, not the code
ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py
pointer only (licence: NONE) · get_code("c97bd6f10fdb8caa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/models/resnet.py
pointer only (licence: NONE) · get_code("4dec1b673b8a327b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

dict_str Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/utils.py
pointer only (licence: NONE) · get_code("bb81c0c5dd65ef6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

focal_loss Ran
ran; our contract draft was wrong, not the code
ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py
pointer only (licence: NONE) · get_code("b6c954a2933604c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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_image_shape Ran
ran, honoured the contract we drafted
ml-stat-sustech/convexconcaveloss/source/examples/mia.py
pointer only (licence: NONE) · get_code("d0e5d7703aefba71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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_loss Ran
ran; our contract draft was wrong, not the code
ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py
pointer only (licence: NONE) · get_code("95e364953588331d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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.

p1_score Ran
ran, honoured the contract we drafted
ml-stat-Sustech/ConvexConcaveLoss/source/utils.py
pointer only (licence: NONE) · get_code("d340646b8b16aabd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

prepare_backdoor_attack Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/data_loader_target.py
pointer only (licence: NONE) · get_code("7b26b959ff1b54da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

prepare_dataset Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/dataset_preprocessing.py
pointer only (licence: NONE) · get_code("0f643892107414ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

prepare_dataset_inference Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/dataset_preprocessing.py
pointer only (licence: NONE) · get_code("ce042b6471ccd220")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

prepare_dataset_ni Ran
ran on a synthesized input
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/dataset_preprocessing.py
pointer only (licence: NONE) · get_code("b91749293b14eb0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

prepare_texas Ran
ran; our contract draft was wrong, not the code
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/data_no_image.py
pointer only (licence: NONE) · get_code("6ee069ade3ca3b94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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.

taylor_exp Ran
ran; our contract draft was wrong, not the code
ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py
pointer only (licence: NONE) · get_code("3f8a0715e9d1a0db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-sustech/convexconcaveloss 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.

prepare_purchase Not yet run
unverified (harvested, no recorded run)
ml-stat-Sustech/ConvexConcaveLoss/source/data_preprocessing/data_no_image.py
pointer only (licence: NONE) · get_code("9330d696182447fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-stat-Sustech/ConvexConcaveLoss 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
conv3x3 15 other papers
11 dated earlier, 4 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1805.04635 (2018-05)
Direction-aware Spatial Context Features for Shadow Detection and Removal
1807.01697 (2018-07)
Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
and 12 more not named here

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 learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent to enlarge the loss variance of training data, alleviating the privacy risk. However, optimizing toward a reverse direction may cause the model parameters to oscillate near local minima, leading to instability and suboptimal performance. In this work, we propose a novel method -Convex-Concave Loss (CCL), which enables a high variance of training loss distribution by gradient descent. Our method is motivated by the theoretical analysis that convex losses tend to decrease the loss variance during training. Thus, our key idea behind CCL is to reduce the convexity of loss functions with a concave term. Trained with CCL, neural networks produce losses with high variance for training data, reinforcing the defense against MIAs. Extensive experiments demonstrate the superiority of CCL, achieving a state-of-the-art balance in the privacy-utility trade-off.

For agents

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

get_harvested_code_for_paper("2402.05453")
get_code_for_paper("2402.05453")
have("2402.05453")

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

curl https://syntology.ai/api/ran/2402.05453.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05453.svg)](https://syntology.ai/paper/2402.05453)

Connect an agent — have() is free.