Papers › On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

15 Jun 2023arXiv:2306.09104archive 2025-07-28

Zhanke Zhou, Chenyu Zhou, Xuan Li, Jiangchao Yao, Quanming Yao, Bo Han

Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored. To close this gap, we perform the first comprehensive study of graph reconstruction attack that aims to reconstruct the adjacency of nodes. We show that a range of factors in GNNs can lead to the surprising leakage of private links. Especially by taking GNNs as a Markov chain and attacking GNNs via a flexible chain approximation, we systematically explore the underneath principles of graph reconstruction attack, and propose two information theory-guided mechanisms: (1) the chain-based attack method with adaptive designs for extracting more private information; (2) the chain-based defense method that sharply reduces the attack fidelity with moderate accuracy loss. Such two objectives disclose a critical belief that to recover better in attack, you must extract more multi-aspect knowledge from the trained GNN; while to learn safer for defense, you must forget more link-sensitive information in training GNNs. Empirically, we achieve state-of-the-art results on six datasets and three common GNNs. The code is publicly available at: https://github.com/tmlr-group/MC-GRA.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of chain-based defense method, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='chain-based defense method') (how to connect); the free check have('2306.09104') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 23 code samples: 22 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 23: 23 ran (of which 3 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 2 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 22 ran (15 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 23 samples that ran has no recorded date.

tmlr-group/mc-gra officialmentioned in papermentioned on GitHubpytorchMITSyntology: 22 samples, 22 ran (7 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested: 23 ran (of which 3 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 2 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
7ran · our draft was wrong
12ran

Licence: 2 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tmlr-group/mc-gra. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

tmlr-group/mc-gra official repository 22 samples, 22 ran (7 instrument-failed) · 0 unverified
BaseAttack in 6 papers MC-GRA/topology_attack.py ran MIT (permissive) · 27b61ad1437b1f9c · report fixture: returned BaseAttack · level recorded 2026-09-22
Info_entropy MC-GRA/topology_attack.py ran · our draft was wrong fingerprinted MIT (permissive) · 06c51c6cdd2e1c83 · report fixture: signature prob:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MutualInformation MC-GRA/topology_attack.py ran MIT (permissive) · 8761bdf3ac0917f1 · report fixture: returned MutualInformation · level recorded 2026-09-22
PGDAttack in 5 papers MC-GRA/topology_attack.py ran MIT (permissive) · 20859a342af81901 · report fixture: returned PGDAttack · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
MC-GRA/models/gat.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 18557871f0c93b3f · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
MC-GRA/topology_attack.py ran · our draft was wrong fingerprinted MIT (permissive) · 2a10125e4bf22807 · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
calc_mrr MC-GRA/gaussian_parameterized.py ran fingerprinted MIT (permissive) · ac45b872d56028b3 · report fixture: signature real_edge:ndarray/1/int, pred_edge:ndarray/1/float · returned float64 · level recorded 2026-09-26
calc_mrr_all MC-GRA/gaussian_parameterized.py ran fingerprinted MIT (permissive) · d147e77a227e1ec8 · report fixture: signature real_edge:ndarray/1/int, pred_edge:ndarray/1/float · returned float64 · level recorded 2026-09-26
distmat in 12 papers
census: 4 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
MC-GRA/hsic.py ran fingerprinted MIT (permissive) · f5d7ba6e6fc594f1 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-26
dot_product_decode in 5 papers MC-GRA/defense/use_model.py ran fingerprinted MIT (permissive) · 6ca867ba81c38181 · report fixture: signature Z:Tensor/2/float · returned Tensor · level recorded 2026-09-26
dot_product_decode in 5 papers MC-GRA/topology_attack.py ran fingerprinted MIT (permissive) · a49a86f5e036e7fe · report fixture: signature Z:Tensor/2/float · returned Tensor · level recorded 2026-09-26
is_sparse_tensor MC-GRA/topology_attack.py ran · violated contract fingerprinted MIT (permissive) · 52dc6af09a603269 · report fixture: signature tensor:Tensor/2/float · returned bool · level recorded 2026-09-22
kernelmat in 10 papers MC-GRA/hsic.py ran fingerprinted MIT (permissive) · e3c0f8ba33d86df6 · report fixture: signature X:Tensor/2/float, sigma:NoneType/0/? · returned Tensor · level recorded 2026-09-26
metric in 14 papers MC-GRA/gaussian_parameterized.py ran MIT (permissive) · ffdd100106716576 · report fixture: signature ori_adj:Tensor/2/float, inference_adj:Tensor/2/float, idx:list/1/int, index_delete:list/1/int · returned Tensor · level recorded 2026-09-26
normalize_adj in 55 papers MC-GRA/topology_attack.py ran · our draft was wrong MIT (permissive) · 6002a1395bc2b25d · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
normalize_adj_tensor MC-GRA/topology_attack.py ran · our draft was wrong fingerprinted MIT (permissive) · efa838a9d8cb2b22 · report fixture: signature adj:Tensor/2/float, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-22
parse_index_file in 54 papers MC-GRA/dataset.py ran · honoured contract MIT (permissive) · 5c3fa9402a9405bc · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-22
sampling_MI MC-GRA/topology_attack.py ran MIT (permissive) · 822a38907beda1d8 · report fixture: signature prob:Tensor/2/float, tau:float/0/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-26
sigma_estimation in 12 papers
census: 4 implementations from 6 papers, 1 distinct output on one shared input
MC-GRA/hsic.py ran fingerprinted MIT (permissive) · 81e80990e0255bc4 · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float · returned float32 · level recorded 2026-09-26
tensor2onehot MC-GRA/topology_attack.py ran · our draft was wrong MIT (permissive) · edde8b8b03e59989 · report fixture: signature labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
to_scipy MC-GRA/topology_attack.py ran · our draft was wrong MIT (permissive) · 3aeda921e3028bde · report fixture: signature tensor:Tensor/2/float · returned csr_matrix · level recorded 2026-09-22
to_tensor in 92 papers
census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
MC-GRA/topology_attack.py ran · our draft was wrong MIT (permissive) · 98b9562f9f93cf6a · report fixture: signature adj:csr_matrix/2/float, features:csr_matrix/2/float, labels:ndarray/1/int, device:str/0/str · returned tuple · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
normalization in 70 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 1, kind float, dtype float64
repository not located ran · violated contract fingerprinted licence of this copy not recorded · 86c7147edb17dd5d · report fixture: signature data:ndarray/1/float · returned ndarray · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for chain-based defense method (graph method: chain-based defense method), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. mc_gra_objective entry · level 3 · ran · honoured contract · 7d67682128ae39280564d2f6260b0d7442ec1b22d12b180d54118431fe4475e4

harvested Assembly for chain-based attack method (graph method: chain-based attack method). 14 bricks; individually on a fixture: 14 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. PGDAttack entry · level 1 · ran · 20859a342af81901
  2. BaseAttack helper · level 1 · ran · 27b61ad1437b1f9c
  3. CudaCKA helper · level 1 · ran · a9e6623f1781245e
  4. Info_entropy loss · level 1 · ran · our draft was wrong · 06c51c6cdd2e1c83
  5. MutualInformation helper · level 1 · ran · 8761bdf3ac0917f1
  6. accuracy helper · level 1 · ran · our draft was wrong · 2a10125e4bf22807
  7. normalize_adj_tensor helper · level 1 · ran · our draft was wrong · efa838a9d8cb2b22
  8. tensor2onehot helper · level 1 · ran · our draft was wrong · edde8b8b03e59989
  9. to_tensor helper · level 1 · ran · our draft was wrong · 98b9562f9f93cf6a
  10. to_scipy helper · level 1 · ran · our draft was wrong · 3aeda921e3028bde
  11. normalization helper · level 1 · ran · violated contract · 86c7147edb17dd5d
  12. normalize_adj helper · level 1 · ran · our draft was wrong · 6002a1395bc2b25d
  13. sparse_mx_to_torch_sparse_tensor helper · level 1 · ran · our draft was wrong · c97b99c4e8201a97
  14. is_sparse_tensor helper · level 1 · ran · violated contract · 52dc6af09a603269

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.09104") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph ReconstructionReconstruction Attack

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections