SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.03429 · 2026

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

Ben Firas, Hmida, Zain Sbeih, Philemon Hailemariam, Birhanu Eshete

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2601.03429.json · badge: /api/ran/2601.03429.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
um-dsp/DeepLeak canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
Saliency_map Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
um-dsp/DeepLeak/xai_methods/captum_wrappers.py
pointer only (licence: NONE) · get_code("b7c2bc1103bbbaa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

create_feature_mask_from_topk Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
um-dsp/DeepLeak/utils/helpers.py
pointer only (licence: NONE) · get_code("42c251429a0be073")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

evaluate_models_with_majority Ran
ran; our contract draft was wrong, not the code
um-dsp/DeepLeak/utils/evaluation.py
pointer only (licence: NONE) · get_code("8b893f70bf4d4bb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

load_data Ran
ran; our contract draft was wrong, not the code
um-dsp/DeepLeak/datasets/dynamic_graph_dataset.py
pointer only (licence: NONE) · get_code("c1b244ba6b64e1ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

normalize_attributions Ran
ran, honoured the contract we drafted
um-dsp/DeepLeak/utils/helpers.py
pointer only (licence: NONE) · get_code("a71944ec36ceb0bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

resnet Ran
ran; our contract draft was wrong, not the code
um-dsp/DeepLeak/models/resnet.py
pointer only (licence: NONE) · get_code("b12e9f0310e4b57a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

summarize_attributions Ran
ran, violated the contract we drafted
um-dsp/DeepLeak/utils/helpers.py
pointer only (licence: NONE) · get_code("841dab2af7882eb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

test Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
um-dsp/DeepLeak/utils/evaluation.py
pointer only (licence: NONE) · get_code("bbe52bfffee9e814")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

to_numpy Ran
ran; our contract draft was wrong, not the code
um-dsp/DeepLeak/xai_methods/captum_wrappers.py
pointer only (licence: NONE) · get_code("44c5627241a36155")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

train_model Ran
ran; our contract draft was wrong, not the code
um-dsp/DeepLeak/utils/training.py
pointer only (licence: NONE) · get_code("076de26c8d8e6171")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

UPANets Not yet run
unverified (harvested, no recorded run)
um-dsp/DeepLeak/models/upanets.py
pointer only (licence: NONE) · get_code("36e498ef22d8f537")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

evaluate_model Not yet run
unverified (harvested, no recorded run)
um-dsp/DeepLeak/utils/evaluation.py
pointer only (licence: NONE) · get_code("9050ce24d753dc98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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.

integrated_gradients Not yet run
unverified (harvested, no recorded run)
um-dsp/DeepLeak/xai_methods/captum_wrappers.py
pointer only (licence: NONE) · get_code("754864e120b68419")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, um-dsp/DeepLeak 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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 2026-11-21.

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 (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between interpretability and privacy. Although prior work has shown that explanation methods can leak membership information, practitioners still lack systematic guidance on selecting or deploying explanation techniques that balance transparency with privacy. We present DeepLeak, a system to audit and mitigate privacy risks in post-hoc explanation methods. DeepLeak advances the state-of-the-art in three ways: (1) comprehensive leakage profiling: we develop a stronger explanation-aware membership inference attack (MIA) to quantify how much representative explanation methods leak membership information under default configurations; (2) lightweight hardening strategies: we introduce practical, model-agnostic mitigations, including sensitivitycalibrated noise, attribution clipping, and masking, that substantially reduce membership leakage while preserving explanation utility; and (3) root-cause analysis: through controlled experiments, we pinpoint algorithmic properties (e.g., attribution sparsity and sensitivity) that drive leakage. Evaluating 15 explanation techniques across four families on image benchmarks, DeepLeak shows that default settings can leak up to 74.9% more membership information than previously reported. Our mitigations cut leakage by up to 95% (minimum 46.5%) with only ≤3.3% utility loss on average. DeepLeak offers a systematic, reproducible path to safer explainability in privacy-sensitive ML.

For agents

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

get_harvested_code_for_paper("2601.03429")
get_code_for_paper("2601.03429")
have("2601.03429")

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

curl https://syntology.ai/api/ran/2601.03429.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.03429.svg)](https://syntology.ai/paper/2601.03429)

Connect an agent — have() is free.