SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.12922 · 2026

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy

Alexander Ziller, Georgios Kaissis, Eleni Triantafillou, Daniel Rückert, Johannes Kaiser

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2601.12922.json · badge: /api/ran/2601.12922.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
Johannes-Kaiser/Collusion-Vuln-in-DP canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_permutation Ran
ran; our contract draft was wrong, not the code
Johannes-Kaiser/Collusion-Vuln-in-DP/opacus_new/layers/dp_rnn.py
pointer only (licence: NONE) · get_code("46783ac8b5216877")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Johannes-Kaiser/Collusion-Vuln-in-DP 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.

filter_out_old_keys Ran
ran; our contract draft was wrong, not the code
Johannes-Kaiser/Collusion-Vuln-in-DP/opacus_new/layers/param_rename.py
pointer only (licence: NONE) · get_code("a20422f8abbda65c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Johannes-Kaiser/Collusion-Vuln-in-DP 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.

shape_safe Ran
ran, honoured the contract we drafted
Johannes-Kaiser/Collusion-Vuln-in-DP/opacus_new/data_loader.py
pointer only (licence: NONE) · get_code("8a8a203a1b2745da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Johannes-Kaiser/Collusion-Vuln-in-DP 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.

wrap_collate_with_empty Ran
ran; our contract draft was wrong, not the code
Johannes-Kaiser/Collusion-Vuln-in-DP/opacus_new/data_loader.py
pointer only (licence: NONE) · get_code("22adb89241969cb8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Johannes-Kaiser/Collusion-Vuln-in-DP 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
apply_permutation 1 other paper
1 dated earlier
2110.05679 (2021-10)
Large Language Models Can Be Strong Differentially Private Learners
filter_out_old_keys 1 other paper
1 dated earlier
2110.05679 (2021-10)
Large Language Models Can Be Strong Differentially Private Learners

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

Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP guarantees, an individual's privacy risk is not solely governed by their own privacy budget, but critically depends on the privacy choices of all other data contributors. This creates a mismatch between the promise of individual privacy control and the reality of a system where risk is collectively determined. We demonstrate empirically that certain distributions of privacy preferences can unintentionally inflate the privacy risk of individuals, even when their formal guarantees are met. Moreover, this excess risk provides an exploitable attack vector. A central adversary or a set of colluding adversaries can deliberately choose privacy budgets to amplify vulnerabilities of targeted individuals. Most importantly, this attack operates entirely within the guarantees of DP, hiding this excess vulnerability. Our empirical evaluation demonstrates successful attacks against 62% of targeted individuals, substantially increasing their membership inference susceptibility. To mitigate this, we propose (εi, δi, ∆)-iDP a privacy contract that uses ∆-divergences to provide users with a hard upper bound on their excess vulnerability, while offering flexibility to mechanism design. Our findings expose a fundamental challenge to the current paradigm, demanding a re-evaluation of how iDP systems are designed, audited, communicated, and deployed to make excess risks transparent and controllable.

For agents

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

get_harvested_code_for_paper("2601.12922")
get_code_for_paper("2601.12922")
have("2601.12922")

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

curl https://syntology.ai/api/ran/2601.12922.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.12922.svg)](https://syntology.ai/paper/2601.12922)

Connect an agent — have() is free.