Paper Citation Record · LEDGER

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks

As of 16 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2507.06525.

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

pith.paper-citation-record.v1
2507.06525 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:06:27.033357Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

26 of 26 outbound references displayed

verified exact3
verified fuzzy12
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 457469f5-8dae-4659-9578-b20f4a7e2af7 · outbound

This paper cites Deep learning with differential privacy.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Deep learning with differential privacy

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.348331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c9a7a396-7340-4430-9ff9-5a3fdb983690 · outbound

This paper cites Towards General Deep Leakage in Federated Learning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Towards General Deep Leakage in Federated Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:25.717574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9871e2-8ac7-4892-8083-bb8a262beaeb · outbound

This paper cites DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:26.125944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 350f5e72-4312-48d2-a9ea-0121bf50fe7f · outbound

This paper cites Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:26.279978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee57e676-084a-4fdd-98e0-09881b960196 · outbound

This paper cites Privacy- preserving deep learning: Revisited and enhanced.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Privacy- preserving deep learning: Revisited and enhanced

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.265174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6c751ce0-90ed-4357-9fba-8e537a34f38f · outbound

This paper cites AdaCliP: Adaptive Clipping for Private SGD.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks AdaCliP: Adaptive Clipping for Private SGD

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:26.464885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da1ee37f-b161-4796-9e79-f1f4f0f8de4a · outbound

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

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:26.543195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6072ef-94c8-4330-9883-8184ed2f10d7 · outbound

This paper cites Machine learning models that remember too much.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Machine learning models that remember too much

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.253985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 05b4a1b9-163c-41e8-8e65-ef69cadf3dd3 · outbound

This paper cites Subsampled rényi differ- ential privacy and analytical moments accountant.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Subsampled rényi differ- ential privacy and analytical moments accountant

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.243363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5f7c4feb-cf55-49d5-9c54-3d218ca22d5c · outbound

This paper cites Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:27.018676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66118899-b1dd-4ad2-94e3-f6141651ead7 · outbound

This paper cites Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:27.022546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecbb342a-1348-42b7-9873-69e375add08b · outbound

This paper cites Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:27.025962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b46e39da-8938-4aef-a4c0-f741e283aec4 · outbound

This paper cites R-GAP: Recursive Gradient Attack on Privacy.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks R-GAP: Recursive Gradient Attack on Privacy

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:27.029681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40617e3f-58ff-45d0-b2b7-21f937a1c405 · outbound

This paper cites Improving Differentially Private SGD via Randomly Sparsified Gradients.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Improving Differentially Private SGD via Randomly Sparsified Gradients

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:06:27.068944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2de95ee1-eef8-46cd-8ec2-11caae514e1a · outbound

This paper cites Deepleakagefromgradientsinmultiple-label medical image classification.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Deepleakagefromgradientsinmultiple-label medical image classification

Reference 1998

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.297742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b2ccfc71-2d5e-4c83-8086-3d429fbda7b1 · outbound

This paper cites FedSel: Federated SGD under local differential privacy with top-k dimension selection.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks FedSel: Federated SGD under local differential privacy with top-k dimension selection

Reference 2005

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.287410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1ac48b0e-05f9-42aa-91de-e43646b6116a · outbound

This paper cites Bagging classifiers for fighting poisoning attacks in adversarial classification tasks.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Bagging classifiers for fighting poisoning attacks in adversarial classification tasks

Reference 2009

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.318415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b77625df-8a98-4e59-b284-ad2deb6e0249 · outbound

This paper cites DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:25.624583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d1d366-1ab1-4594-8f5d-3ad38bcf588b · outbound

This paper cites Differential Privacy Meets Neural Network Pruning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Differential Privacy Meets Neural Network Pruning

Reference 2016

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:06:27.220633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d1db8e4f-697d-434b-8220-c5dc7f01de0c · outbound

This paper cites Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.276413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0e0dc86d-5a34-4254-adb7-65cde4b4b827 · outbound

This paper cites PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance

Reference 2018

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:06:27.128664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ef1dd743-873a-41ef-b270-edd163578ee7 · outbound

This paper cites Privacy-preserving Learning via Deep Net Pruning.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Privacy-preserving Learning via Deep Net Pruning

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T19:06:25.820295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51314688-92bf-46f6-be46-44e4a04b5cd7 · outbound

This paper cites Secure multi-party computation problems and their applications: a review and open problems.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Secure multi-party computation problems and their applications: a review and open problems

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.307902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9dc4be5a-27df-41f4-9240-431d591dc4fb · outbound

This paper cites Can machine learning be secure? InProceedings of the 2006 ACM Symposium on Information, computer and communications security, pages 16–25,.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Can machine learning be secure? InProceedings of the 2006 ACM Symposium on Information, computer and communications security, pages 16–25,

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.338170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff2e485f-f443-4456-a983-cda518eeec6e · outbound

This paper cites Bolt-on differential privacy for scalable stochastic gradient descent-based analytics.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Bolt-on differential privacy for scalable stochastic gradient descent-based analytics

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.231994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5e5c86d0-be36-4376-8bfd-a89eba0bb6db · outbound

This paper cites Multiple classifier systems for adversarial classification tasks.

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks Multiple classifier systems for adversarial classification tasks

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:06:27.327710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.