Paper Citation Record · LEDGER

Machine Learning with Privacy for Protected Attributes

As of 17 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2506.19836.

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

pith.paper-citation-record.v1
2506.19836 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:39:11.512973Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

40 of 40 outbound references displayed

verified exact3
verified fuzzy24
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b63d38ef-3642-41ca-a18d-60b490cac01d · outbound

This paper cites Deep learning with differential privacy.

Machine Learning with Privacy for Protected Attributes Deep learning with differential privacy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.337641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3ff84b-d9dc-4760-a0f7-a1807bfbb3c3 · outbound

This paper cites Pri- vacy amplification by subsampling: Tight analyses via couplings and divergences.

Machine Learning with Privacy for Protected Attributes Pri- vacy amplification by subsampling: Tight analyses via couplings and divergences

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:12.050746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2343b987-2662-4fe2-bcf6-9698aac5ade3 · outbound

This paper cites Private stochastic convex optimization with optimal rates.

Machine Learning with Privacy for Protected Attributes Private stochastic convex optimization with optimal rates

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:12.037515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ba4d3bdf-096f-4f72-b27b-b4b886ca87e1 · outbound

This paper cites Broadening the scope of differential privacy using metrics.

Machine Learning with Privacy for Protected Attributes Broadening the scope of differential privacy using metrics

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:12.024056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 496e2c7f-fd8f-435e-a297-5d3c9abf517d · outbound

This paper cites On the relationships between no- tions of simulation-based security.

Machine Learning with Privacy for Protected Attributes On the relationships between no- tions of simulation-based security

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:12.010840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9fe58ce3-6247-4293-a0dd-ae3c6d2379d5 · outbound

This paper cites Unlocking High-Accuracy Differentially Private Image Classification through Scale.

Machine Learning with Privacy for Protected Attributes Unlocking High-Accuracy Differentially Private Image Classification through Scale

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.363771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012a1038-9c87-4aec-a137-8786b9e7d69e · outbound

This paper cites Gaussian Differential Privacy.

Machine Learning with Privacy for Protected Attributes Gaussian Differential Privacy

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.368659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee73f2d-a68d-49c0-b593-55bae5e389c7 · outbound

This paper cites Differential privacy.

Machine Learning with Privacy for Protected Attributes Differential privacy

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.997615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f68d1b85-816a-408a-9aa0-049616cff5a1 · outbound

This paper cites Why is public pretraining necessary for private model training? In Interna- tional Conference on Machine Learning, pages 10611– 10627.

Machine Learning with Privacy for Protected Attributes Why is public pretraining necessary for private model training? In Interna- tional Conference on Machine Learning, pages 10611– 10627

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.985514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2da74714-39dd-4cb3-a608-f312f33721d0 · outbound

This paper cites Property inference attacks on fully connected neural networks using permutation invariant representations.

Machine Learning with Privacy for Protected Attributes Property inference attacks on fully connected neural networks using permutation invariant representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.382625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfb60799-591a-478f-8eb8-6f5e917d2c22 · outbound

This paper cites Differentially Private Diffusion Models Generate Useful Synthetic Images.

Machine Learning with Privacy for Protected Attributes Differentially Private Diffusion Models Generate Useful Synthetic Images

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.386421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7fcf191-7c49-4232-ad5b-e92e20d79262 · outbound

This paper cites Deep learning with label differential privacy.

Machine Learning with Privacy for Protected Attributes Deep learning with label differential privacy

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.964984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 899d6dc7-909c-4fec-8823-10cc9d8fd7e0 · outbound

This paper cites Algorithms with More Granular Differential Privacy Guarantees.

Machine Learning with Privacy for Protected Attributes Algorithms with More Granular Differential Privacy Guarantees

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:39:11.653870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d24899e4-0cd5-454e-b079-bba7d6305522 · outbound

This paper cites Inferential Privacy Guarantees for Differentially Private Mechanisms.

Machine Learning with Privacy for Protected Attributes Inferential Privacy Guarantees for Differentially Private Mechanisms

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:39:11.633989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 938f6768-cf40-4aaa-8d3f-ada0f273b2ab · outbound

This paper cites Numerical composition of differential privacy.

Machine Learning with Privacy for Protected Attributes Numerical composition of differential privacy

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.952575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4916a56c-dea4-4305-bd50-d5b357a6dcf7 · outbound

This paper cites Bounding training data re- construction in private (deep) learning.

Machine Learning with Privacy for Protected Attributes Bounding training data re- construction in private (deep) learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.938496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 043e498c-1b50-4783-bf5c-bb06543fbb8d · outbound

This paper cites Bounding training data reconstruction in dp-sgd.

Machine Learning with Privacy for Protected Attributes Bounding training data reconstruction in dp-sgd

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.923478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 07ef4124-7e6e-47bc-85bf-5def289bcded · outbound

This paper cites Are attribute inference attacks just imputation? In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pages 1569–1582, 2022.

Machine Learning with Privacy for Protected Attributes Are attribute inference attacks just imputation? In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pages 1569–1582, 2022

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.907490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d3ae3943-1dc9-493a-84cb-23a47c7dc65e · outbound

This paper cites {AttriGuard}: A practical defense against attribute inference attacks via adversarial machine learning.

Machine Learning with Privacy for Protected Attributes {AttriGuard}: A practical defense against attribute inference attacks via adversarial machine learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.894415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6729356e-bd18-413e-8e1b-639810070269 · outbound

This paper cites Private convex empirical risk minimization and high- dimensional regression.

Machine Learning with Privacy for Protected Attributes Private convex empirical risk minimization and high- dimensional regression

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.882699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 54e77845-7a2c-4569-bd4c-15fda8eefb36 · outbound

This paper cites Private Learning with Public Features.

Machine Learning with Privacy for Protected Attributes Private Learning with Public Features

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.427865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7485d049-53f0-4fa0-bfb6-2070bcad2ab6 · outbound

This paper cites Large Language Models Can Be Strong Differentially Private Learners.

Machine Learning with Privacy for Protected Attributes Large Language Models Can Be Strong Differentially Private Learners

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.431975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e102cb-06fb-44cc-b02b-efb3d54ea117 · outbound

This paper cites Distributional privacy for data sharing.

Machine Learning with Privacy for Protected Attributes Distributional privacy for data sharing

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.870781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 19817a37-a71e-4d66-a5a9-06d946c806b2 · outbound

This paper cites Property inference from poisoning.

Machine Learning with Privacy for Protected Attributes Property inference from poisoning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.859140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8593507f-7a4c-4ace-b400-87e10e0b6f10 · outbound

This paper cites Antipodes of label differential privacy: Pate and alibi.

Machine Learning with Privacy for Protected Attributes Antipodes of label differential privacy: Pate and alibi

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.847445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4b136916-2d23-4f1b-ab65-47ec9478b2e6 · outbound

This paper cites Not all features are equal: Discovering essential features for preserving prediction privacy.

Machine Learning with Privacy for Protected Attributes Not all features are equal: Discovering essential features for preserving prediction privacy

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.835994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0c09a8b2-e2ac-4663-bc31-3ee5bdc282e5 · outbound

This paper cites Stochastic gradient descent for non-smooth optimization: Convergence re- sults and optimal averaging schemes.

Machine Learning with Privacy for Protected Attributes Stochastic gradient descent for non-smooth optimization: Convergence re- sults and optimal averaging schemes

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.823287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 02377e32-d5e9-4847-9dcd-688601cc2949 · outbound

This paper cites Selective Differential Privacy for Language Modeling.

Machine Learning with Privacy for Protected Attributes Selective Differential Privacy for Language Modeling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.460192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9c06199-39e5-4b68-9502-28ee5a0db4c5 · outbound

This paper cites Stochastic gradient descent with differentially private updates.

Machine Learning with Privacy for Protected Attributes Stochastic gradient descent with differentially private updates

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.809122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7923fdc2-f25d-4835-8ce7-02084577d7d7 · outbound

This paper cites Machine learning with differentially private labels: Mechanisms and frameworks.

Machine Learning with Privacy for Protected Attributes Machine learning with differentially private labels: Mechanisms and frameworks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.795112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9bb085cd-7b5c-4961-83b5-01c67466fc77 · outbound

This paper cites Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition.

Machine Learning with Privacy for Protected Attributes Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.472955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6c1182-7dfd-41df-b91a-d8eef087273b · outbound

This paper cites A Randomized Approach for Tight Privacy Accounting.

Machine Learning with Privacy for Protected Attributes A Randomized Approach for Tight Privacy Accounting

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:39:11.566090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 14b26a9b-c696-483e-8211-fbaac99cc077 · outbound

This paper cites A study of face obfuscation in imagenet.

Machine Learning with Privacy for Protected Attributes A study of face obfuscation in imagenet

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.782555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dbd68a31-c612-4b31-8af6-aeee9d488568 · outbound

This paper cites ViP: A Differentially Private Foundation Model for Computer Vision.

Machine Learning with Privacy for Protected Attributes ViP: A Differentially Private Foundation Model for Computer Vision

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:11.486572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd2078a-c2c9-4d5f-9332-e734bc98f034 · outbound

This paper cites Attribute privacy: Framework and mechanisms.

Machine Learning with Privacy for Protected Attributes Attribute privacy: Framework and mechanisms

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.768361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f3e3ce7a-31fc-4c82-958f-fb5004d87985 · outbound

This paper cites Opti- mal accounting of differential privacy via characteristic function.

Machine Learning with Privacy for Protected Attributes Opti- mal accounting of differential privacy via characteristic function

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.754881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e7a0447a-4af2-4e7d-b02e-d12e4511c4c1 · outbound

This paper cites Feature Differential Privacy.

Machine Learning with Privacy for Protected Attributes Feature Differential Privacy

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:39:11.742048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1f680f1a-be39-461c-a67d-8d517616f59d · outbound

This paper cites an unresolved cited work.

Machine Learning with Privacy for Protected Attributes Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:39:11.729477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2710cf82-4489-4dac-9a04-96482b802bb7 · outbound

This paper cites an unresolved cited work.

Machine Learning with Privacy for Protected Attributes Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:39:11.717107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5137210c-bf0e-4d33-9570-87440b29726a · outbound

This paper cites an unresolved cited work.

Machine Learning with Privacy for Protected Attributes Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:39:11.703540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.