Pith. sign in

Paper Citation Record · LEDGER

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

As of 21 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2502.03692.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.03692 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:11:59.896263Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

  • verified exact0
  • verified fuzzy15
  • unresolved11
  • parse uncertain0
  • malformed identifier4
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5292b97f-28d0-4115-aa06-36733e36f6ea · outbound

This paper cites Deep learning with differential privacy.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Deep learning with differential privacy

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.794025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.794025Z digest=sha256:b9cc51e8b2635b56492d2d7760f3794cc04ccce4c3d6c3b2eb1c43ea7df99f51

Observation ae1bc712-aafa-476f-9cac-2ba6c2381dde · outbound

This paper cites Practical Blind Membership Inference Attack via Differential Comparisons.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Practical Blind Membership Inference Attack via Differential Comparisons

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.806746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.806746Z digest=sha256:3b2411ebb9b64f3e6b2e028467ab60400032d0ef406f051abc280b412120cd03

Observation 8c02bdad-91c3-44e4-b1e2-ad7d84393945 · outbound

This paper cites an unresolved cited work.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Unresolved cited work

Reference 6

Resolution
malformed identifier
raw_fallback, observed 2026-08-09T04:12:00.056014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.876810Z digest=sha256:f232950b92efaf4b31f9acdee95de0fda802266c927d2b550a02e7f8b19cf314

Observation 8c89f7fe-e93c-44d9-83e0-0c6743030574 · outbound

This paper cites an unresolved cited work.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-09T04:12:00.044900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.880462Z digest=sha256:78fa2d609701f2c75c2f4884fa776fc207efd9c2dd5506607e9a6eab6c8fe034

Observation 2e1df3a0-91f5-4a7d-85a3-2a574ff0878f · outbound

This paper cites Adam: A Method for Stochastic Optimization.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Adam: A Method for Stochastic Optimization

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.819992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.819992Z digest=sha256:67f244e40ab66016811cd82cf7601fdf5c062768655cefa44458500f72bd0825

Observation d5bc730e-3c09-4456-ae62-cf6315a4c8cd · outbound

This paper cites Pix2struct: screenshot pars- ing as pretraining for visual language understanding.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Pix2struct: screenshot pars- ing as pretraining for visual language understanding

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.171678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.823792Z digest=sha256:b035e53dd78179540a9f20c6ce0d37959b6b5f26c56ab3f5cc58e209a67c84bb

Observation 8c40ab5a-3f84-44d5-8703-873fcf225f64 · outbound

This paper cites Membership leakage in label-only exposures.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Membership leakage in label-only exposures

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.161503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.827760Z digest=sha256:cad85f376b025bead4f2ae55660fb339c11f8a5ace1477ed7d136085c7c9ab21

Observation 8ed4da1e-48eb-4391-ba47-9a59dc4d856b · outbound

This paper cites ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.835732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.835732Z digest=sha256:b66d8718c1495870b8c427948c63c41f8dcbd0a280740b672e98a5080fd4ccbc

Observation 6b54f0e4-472c-4370-bf52-6f2417bacf39 · outbound

This paper cites Membership inference at- tacks against machine learning models.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Membership inference at- tacks against machine learning models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.151798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.843997Z digest=sha256:f025fea36468970577f38faa242a49e170ece90f37530975eb72815e70a2f9ab

Observation 3c2752d8-4931-495b-921f-cfec66c5b0f5 · outbound

This paper cites Privacy risks of securing machine learning models against adversarial examples.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Privacy risks of securing machine learning models against adversarial examples

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.141952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.847335Z digest=sha256:36c12f634af76d357f53b2672fa7794ce4be84d31b3bbe8ac22fe915e8713269

Observation f2f640e7-bb83-4b6d-a399-370a91f7a8b5 · outbound

This paper cites Privacy-aware document visual question answering.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Privacy-aware document visual question answering

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.132255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.850228Z digest=sha256:c4718b79a8d5d1b82bd9939212c0e5382b17d062a99c5e7624823776d07be2dc

Observation 0fd6fd4d-e93a-40d4-9deb-5642fe253508 · outbound

This paper cites Transformers: State-of-the-art natural language processing.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Transformers: State-of-the-art natural language processing

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.121915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.852809Z digest=sha256:94a563ce4eac4dacff84b4098c704e04cc00aee0d1993d923b981eb28021dedf

Observation 06f66321-b3a6-4599-ab03-38691d254a4a · outbound

This paper cites Jiayuan Ye, Aadyaa Maddi, Sasi Kumar Murakonda, Vincent Bindschaedler, and Reza Shokri.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Jiayuan Ye, Aadyaa Maddi, Sasi Kumar Murakonda, Vincent Bindschaedler, and Reza Shokri

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.112784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.855646Z digest=sha256:d85e16466487741cfaa825f62fd229236162829db6f686cf318a83e530e3aaab

Observation 63f8db0d-2f2a-4354-9025-82baf10a8c31 · outbound

This paper cites Privacy risk in machine learn- ing: Analyzing the connection to overfitting.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Privacy risk in machine learn- ing: Analyzing the connection to overfitting

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.104207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.858724Z digest=sha256:f5480aa9a2809559ae83d74ca51dc9e92515e241642cffbad3effbc5e5c71da6

Observation b20cd380-7302-4846-bcfb-40d6757d1a3e · outbound

This paper cites Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.861601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.861601Z digest=sha256:5ed21226e6f3567be00f01926622c44cd3d06985136fb286f28b1189bdf58777

Observation 430cdd23-75e6-423b-b850-f28289dc51f4 · outbound

This paper cites This dataset is specifically designed for DocVQA tasks in a federated learning and differential privacy setup, supporting different levels of privacy granularity.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models This dataset is specifically designed for DocVQA tasks in a federated learning and differential privacy setup, supporting different levels of privacy granularity

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.087095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.867705Z digest=sha256:ae332648df732339c687bd286070ce4c7943a425cea9835fa9ae5e312cd48529

Observation 4b494339-352e-4e1f-a9c7-a86133a6a16d · outbound

This paper cites A document is predicted as a member if ¯l ≤ κ and otherwise non-member, where κ is selected as the average value of ¯l across Dtest.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models A document is predicted as a member if ¯l ≤ κ and otherwise non-member, where κ is selected as the average value of ¯l across Dtest

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.077852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.870667Z digest=sha256:f5680e091b8b8bb22c103e851a9ab2024bafb174303635199aec9a9e52c44320

Observation c199b3a0-88c0-46ab-b629-3fddbc2dd56c · outbound

This paper cites We first study the effect of α, which controls the speed of the optimization process in our attacks.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models We first study the effect of α, which controls the speed of the optimization process in our attacks

Reference 24

Resolution
malformed identifier
raw_fallback, observed 2026-08-09T04:12:00.066316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.873551Z digest=sha256:14964b5fd19a245fd3599c068d9bf1be10cec479b11741af7baba7206701c525

Observation 01b32270-281a-4ba8-a72b-fb6580df11cf · outbound

This paper cites Table 10 presents the target models’ performance across both DocVQA datasets.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Table 10 presents the target models’ performance across both DocVQA datasets

Reference 27

Resolution
malformed identifier
raw_fallback, observed 2026-08-09T04:12:00.034307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.883930Z digest=sha256:a84103ba56d46e02a886fc44bf3fb64585c5aed5fa526f4f1d12c5fc7a11079e

Observation 8e93a756-94b8-4723-a315-ade09726015b · outbound

This paper cites total amount.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models total amount

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.025283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.887378Z digest=sha256:05a2b53c23527440c9519835653ce3ef643545fa382b125c908acc5e6350ad18

Observation b2971672-e865-4a87-8b1e-6a9fb8f9f92e · outbound

This paper cites The expectation is that the proxy model can capture internal decision-making patterns by following the black-box’s prediction strategies.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models The expectation is that the proxy model can capture internal decision-making patterns by following the black-box’s prediction strategies

Reference 29

Resolution
malformed identifier
raw_fallback, observed 2026-08-09T04:12:00.015558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.892081Z digest=sha256:96dbef97d6c2a76741e70b5ca9314273286d907ff41d2c415ef6cbcabeec8768

Observation 5e4a267e-b7d4-475e-bb75-4e65b1a8db2a · outbound

This paper cites For additional details on the effects of document resolution, we refer readers to the original model’s paper(Kim et al., 2022).

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models For additional details on the effects of document resolution, we refer readers to the original model’s paper(Kim et al., 2022)

Reference 1920

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.004653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.896263Z digest=sha256:a5a116b8343dc106dee5475fd5eb3f6b81c1c7c8457aacad12194f2cec5453c7

Observation 914982c4-33cb-4601-9baf-534fbe4916ec · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.803351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.803351Z digest=sha256:82679a8e4e53cc9c6e362bbe778b5c341676ecc6439b591f845f179a07618dc8

Observation d5bf5c8f-a12a-4857-8bc8-ac38ec37b8a4 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Detecting Pretraining Data from Large Language Models

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.839508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.839508Z digest=sha256:90dc72c9560b0aa850acda304c4e087be93ab061da3a6f3931fc05bbb70aa26a

Observation 07423aa9-baf6-4d1b-92f1-451b9ecc8d5f · outbound

This paper cites Mem- bership inference attacks from first principles.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Mem- bership inference attacks from first principles

Reference 2019

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.196877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.797612Z digest=sha256:7c8d11c1dbaccbf1bd8368385cc0ff485730d1e695d3fd78b0cf04c49cb2a081

Observation 5d6983ea-fa58-4865-8666-ca3b144af07f · outbound

This paper cites Document Visual Question Answering Challenge 2020.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Document Visual Question Answering Challenge 2020

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.831474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.831474Z digest=sha256:12174ddf68ccc4a63494804a2fe50136afe7e68f7cf68fe800c9d45d5225f3ac

Observation e90ac771-a585-4877-b33a-2e780f03993f · outbound

This paper cites Mistral 7B.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Mistral 7B

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.810754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.810754Z digest=sha256:8d758b4399b60ae94d434b7f55b424ae3be8f9a80c233060193e49efa70e1b38

Observation d0ef42f1-2863-41f2-ae06-05364fd9965d · outbound

This paper cites Label-only membership inference attacks.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Label-only membership inference attacks

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-09T04:11:59.800472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T04:11:59.800472Z digest=sha256:68f02b8c297b9cc5886b0726a289ce4e1364cebc75b5f29d852eb712a2448fcc

Observation ca89db49-8ef5-47f8-bee3-cbd40afb50ae · outbound

This paper cites Ocr-free document un- derstanding transformer.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models Ocr-free document un- derstanding transformer

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.182025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.815862Z digest=sha256:731929e8a806d9b945ff3d93f713c481baa43966d3038dd5141c52156b7a2480

Observation 3cd7fcbe-9fb0-45f0-85e4-9ffc2d424ed6 · outbound

This paper cites 18 D.2 Target Model Performance on DocVQA.

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models 18 D.2 Target Model Performance on DocVQA

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T04:12:00.095378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T04:11:59.864668Z digest=sha256:10549dea9f815469e6bdb74c2d1a886e71026201f71881c8d4d801d1d222e855

Pith citing papers

No inbound Pith citation observations are available.