Paper Citation Record · LEDGER

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run

As of 7 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2507.04457.

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

pith.paper-citation-record.v1
2507.04457 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:55:22.394737Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

41 of 41 outbound references displayed

verified exact0
verified fuzzy24
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 110e5288-8e8e-42c7-89b1-349b24f7f22e · outbound

This paper cites Deep leakage from gradients,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Deep leakage from gradients,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:20.978883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04eef019-85f1-485e-b1af-36e980284a88 · outbound

This paper cites Membership inference attacks from first principles,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Membership inference attacks from first principles,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.716053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 01272a34-42cd-4ca4-b6f4-0aacb8d9843f · outbound

This paper cites Extracting training data from large language models,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Extracting training data from large language models,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:21.200248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8b2bd38-afbd-4e4d-a013-1867307e3f3e · outbound

This paper cites Deep learning with differential privacy,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Deep learning with differential privacy,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.703517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 51235394-36f9-4270-b232-ae9c81a5e1e6 · outbound

This paper cites Calibrating noise to sensitivity in private data analysis,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Calibrating noise to sensitivity in private data analysis,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:21.424481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fd3cc2-9136-4663-a6c2-8ea61f4032f5 · outbound

This paper cites Membership inference attacks against machine learning models,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Membership inference attacks against machine learning models,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:21.546237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46add53-69fa-4d0f-bce7-1bc4b1b6c72d · outbound

This paper cites Debugging Differential Privacy: A Case Study for Privacy Auditing.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Debugging Differential Privacy: A Case Study for Privacy Auditing

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:21.676251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd549248-3780-43a1-a885-4df0fe8add77 · outbound

This paper cites Auditing differentially private machine learning: How private is private sgd?.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Auditing differentially private machine learning: How private is private sgd?

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.685528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 129c6012-269c-4564-80a8-f27b5a83aaf8 · outbound

This paper cites Adversary instantiation: Lower bounds for differentially private machine learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Adversary instantiation: Lower bounds for differentially private machine learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.678395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c3281c5-51ab-4cfb-bf19-67673fa0be25 · outbound

This paper cites Tight auditing of differentially private machine learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Tight auditing of differentially private machine learning,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.670981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 286a6da2-c482-458c-b475-ed14557e1fa8 · outbound

This paper cites Privacy auditing with one (1) training run,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Privacy auditing with one (1) training run,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.663399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a70fa8be-ff8f-4ee1-a5a9-444395dbbd3a · outbound

This paper cites Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.312619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cf518a0-a621-4def-a6c2-b7fd6b7491e1 · outbound

This paper cites Auditing $f$-Differential Privacy in One Run.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Auditing $f$-Differential Privacy in One Run

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.315899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6b06ca-aa7f-4747-9eb9-62ad605eff6f · outbound

This paper cites Nearly tight black- box auditing of differentially private machine learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Nearly tight black- box auditing of differentially private machine learning,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.656213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a50c7f5-3ab7-4f62-bbb1-7d1ed082e6b0 · outbound

This paper cites Differentially private in- context learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Differentially private in- context learning,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.648131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6810905a-421d-4338-a2d4-012a6f72a04c · outbound

This paper cites Evaluating differentially private machine learning in practice,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Evaluating differentially private machine learning in practice,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.640961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41b993fa-acd2-4d9b-94e2-18f445d09d85 · outbound

This paper cites CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.328035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea1c3d7-ac6d-4e7e-be1a-077b83edd05d · outbound

This paper cites A general framework for auditing differentially private machine learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run A general framework for auditing differentially private machine learning,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.633540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bcf5a770-493b-44b4-9dbf-bd24342d7b14 · outbound

This paper cites Bayesian estimation of differential privacy,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Bayesian estimation of differential privacy,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.626321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 101de698-4ea4-45a7-9e7d-cf42dc9236fa · outbound

This paper cites One-shot Empirical Privacy Estimation for Federated Learning.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run One-shot Empirical Privacy Estimation for Federated Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.336968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36c365b2-02b3-4c71-9038-e64aa989648d · outbound

This paper cites Unleashing the power of randomization in auditing differentially private ml,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Unleashing the power of randomization in auditing differentially private ml,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.619038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d032cb6-69c8-4f49-9c3c-bcf7a8b7cfff · outbound

This paper cites Precurious: How innocent pre-trained language models turn into privacy traps,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Precurious: How innocent pre-trained language models turn into privacy traps,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.611219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 243ac1f8-b04f-4db5-83eb-4ca76a754df5 · outbound

This paper cites Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.345690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acffb77b-2c28-425d-b01a-4554ad218dcf · outbound

This paper cites A general framework for data-use auditing of ml models,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run A general framework for data-use auditing of ml models,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.603600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 039a17cc-9ca2-426f-b08b-00ff269d8411 · outbound

This paper cites How much of my dataset did you use? quantitative data usage inference in machine learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run How much of my dataset did you use? quantitative data usage inference in machine learning,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.596017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fdec50f8-0432-4312-9f23-e4f60724e350 · outbound

This paper cites Membership encoding for deep learning,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Membership encoding for deep learning,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.587873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b1f82006-725b-4ffb-8a7e-897a2be2747e · outbound

This paper cites A Method to Facilitate Membership Inference Attacks in Deep Learning Models.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run A Method to Facilitate Membership Inference Attacks in Deep Learning Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.356667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45bdd018-5ebb-4f49-ad2c-00bb7be94070 · outbound

This paper cites The composition theorem for differential privacy,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run The composition theorem for differential privacy,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.580267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 105dc0bd-4ec0-4a5a-a995-280a06886710 · outbound

This paper cites Privacy Auditing of Large Language Models.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Privacy Auditing of Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.361879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422b639a-2c8e-4e3b-ae49-e290b65d6e71 · outbound

This paper cites On the generalization effects of linear transformations in data augmentation,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run On the generalization effects of linear transformations in data augmentation,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.571498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d34bfff9-ee0c-4d58-b0d4-746ba7b72f81 · outbound

This paper cites Understanding deep learning requires rethinking generalization.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Understanding deep learning requires rethinking generalization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.367130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb2ee51a-173e-48b2-b66c-c41e23b01524 · outbound

This paper cites Introduction to modern cryptography,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Introduction to modern cryptography,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.563304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b53bfe7f-af37-4358-9f7a-a029054a10a3 · outbound

This paper cites A new linear scaling rule for private adaptive hyperparameter optimization,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run A new linear scaling rule for private adaptive hyperparameter optimization,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.554653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb981178-d3fd-47d8-b0ed-cda771121a54 · outbound

This paper cites Tem- pered sigmoid activations for deep learning with differential privacy,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Tem- pered sigmoid activations for deep learning with differential privacy,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.546793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 432c2bc9-da6c-45c4-b611-81283fb70379 · outbound

This paper cites Not all noise is accounted equally: How differentially private learning benefits from large sampling rates,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Not all noise is accounted equally: How differentially private learning benefits from large sampling rates,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.538865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a43b512d-b898-4d85-a0ef-abdc5c14c54b · outbound

This paper cites Automatic clipping: Differentially private deep learning made easier and stronger,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Automatic clipping: Differentially private deep learning made easier and stronger,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.530346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c7911ebe-fd40-4a64-8789-34615d912db4 · outbound

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

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Unlocking High-Accuracy Differentially Private Image Classification through Scale

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.383187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a86bd82-d36c-4a5e-b5fb-bf8e24e3b999 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.386349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e5cb4a4-ee64-4fbd-acfc-4b38d7ec094c · outbound

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

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Large Language Models Can Be Strong Differentially Private Learners

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.389023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72334dde-4aeb-4828-bb98-e7f44ac1b050 · outbound

This paper cites Differentially Private Fine-tuning of Language Models.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Differentially Private Fine-tuning of Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.392076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45a72dfd-8d58-4015-9b5e-55b23a40dabe · outbound

This paper cites Meddialog: Large-scale medical dialogue datasets,.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Meddialog: Large-scale medical dialogue datasets,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:55:22.521981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.