Paper Citation Record · LEDGER

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage

As of 9 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2505.20026.

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

pith.paper-citation-record.v1
2505.20026 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:06:30.120001Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

32 of 32 outbound references displayed

verified exact1
verified fuzzy17
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation feae195a-1416-4e98-9331-a1e7ce276949 · outbound

This paper cites Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital–a real life proof of concept.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital–a real life proof of concept

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:33.671712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a724989a-a1eb-4a6d-83da-e7373cf5bdff · outbound

This paper cites Communication- efficient learning of deep networks from decentralized data.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Communication- efficient learning of deep networks from decentralized data

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:27.366988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d15bb50a-7049-4dce-afb3-7d26d56046db · outbound

This paper cites Ffd: A federated learning based method for credit card fraud detection.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Ffd: A federated learning based method for credit card fraud detection

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:33.481987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 77f84dc3-4393-42e1-8874-5e91574c03f6 · outbound

This paper cites Evaluating gradient inversion attacks and defenses in federated learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Evaluating gradient inversion attacks and defenses in federated learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:33.339386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fc27139c-ac2e-4110-b16e-26205354ef56 · outbound

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

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Privacy-preserving deep learning: Revisited and enhanced

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:33.116197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 548d251a-4939-4972-aaa1-baa552e41abc · outbound

This paper cites Deep leakage from gradients.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Deep leakage from gradients

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.966565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c339bb25-a87d-48e9-9333-c7eea890e729 · outbound

This paper cites iDLG: Improved Deep Leakage from Gradients.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage iDLG: Improved Deep Leakage from Gradients

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:27.811626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cbc31c3-5fd6-4f4b-8c29-215e6d3adb96 · outbound

This paper cites A Framework for Evaluating Gradient Leakage Attacks in Federated Learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:27.887385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6627546-2540-4285-bc83-843acda0632e · outbound

This paper cites Inverting gradients-how easy is it to break privacy in federated learning? Advances in neural information processing systems, 33:16937–16947, 2020.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Inverting gradients-how easy is it to break privacy in federated learning? Advances in neural information processing systems, 33:16937–16947, 2020

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.788212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a2f05dba-2408-48c4-aad4-9d3db28e9330 · outbound

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

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage R-GAP: Recursive Gradient Attack on Privacy

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:28.062115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a3d0db-911c-40e5-a9e9-ebb9ecdc70fa · outbound

This paper cites SAPAG: A Self-Adaptive Privacy Attack From Gradients.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage SAPAG: A Self-Adaptive Privacy Attack From Gradients

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:28.160205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c9554b-9639-42a4-87b7-c267ef817456 · outbound

This paper cites See through gradients: Image batch recovery via gradinversion.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage See through gradients: Image batch recovery via gradinversion

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.606312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 00e65b3b-b8d4-4e22-8a5c-f0407880485f · outbound

This paper cites Reconstructing training data from model gradient, provably.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Reconstructing training data from model gradient, provably

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:28.354308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb52a7e-a433-4af1-9dcb-8834c2732f80 · outbound

This paper cites Gradient inversion with generative image prior.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Gradient inversion with generative image prior

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.457899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bedd3438-6171-47cb-842f-feeb15d14f71 · outbound

This paper cites Auditing privacy defenses in federated learning via generative gradient leakage.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Auditing privacy defenses in federated learning via generative gradient leakage

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.291423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d6cb671a-5d76-43fe-b1ac-69a511bb1e23 · outbound

This paper cites Gifd: A generative gradient inversion method with feature domain optimization.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Gifd: A generative gradient inversion method with feature domain optimization

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:32.125362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a4be98e7-129b-476b-9342-06f8ddee041a · outbound

This paper cites Learning to invert: Simple adaptive attacks for gradient inversion in federated learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Learning to invert: Simple adaptive attacks for gradient inversion in federated learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:31.925448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0e281faa-3b5c-439c-b0a3-67e644b272fa · outbound

This paper cites Recovering Labels from Local Updates in Federated Learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Recovering Labels from Local Updates in Federated Learning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:06:30.321191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8c26d8f4-c6d3-49bd-ae37-27ec969c6c2b · outbound

This paper cites Dggi: Deep generative gradient inversion with diffusion model.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Dggi: Deep generative gradient inversion with diffusion model

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:31.589187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30c5e910-074d-4d82-a0fe-fa86eb9871cb · outbound

This paper cites The perceptron: a probabilistic model for information storage and organization in the brain.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage The perceptron: a probabilistic model for information storage and organization in the brain

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:31.295202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36789cda-e3ac-48b4-b919-d1f4e1350afd · outbound

This paper cites Deep learning with differential privacy.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Deep learning with differential privacy

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:29.178669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 281bbce8-dc9c-4527-b3eb-4a07d4e9d6c8 · outbound

This paper cites Reconstructing training data from trained neural networks.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Reconstructing training data from trained neural networks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:30.960199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 526a46e8-98a3-47f1-ba3a-793aa2c094d9 · outbound

This paper cites Instance-wise batch label restoration via gradients in federated learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Instance-wise batch label restoration via gradients in federated learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:30.773624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d9f0e4c3-fa4a-415e-ab85-bb4857765b7b · outbound

This paper cites Spear: Exact gradient inversion of batches in federated learning.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Spear: Exact gradient inversion of batches in federated learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:30.631206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 712f1ec3-a6a0-4347-896a-29800ea844ff · outbound

This paper cites Generative adversarial nets.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Generative adversarial nets

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:29.585116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600d00ac-c814-45af-8d67-a203bf84e980 · outbound

This paper cites Attention is all you need.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Attention is all you need

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:29.697225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a360c63-1a3e-4f53-9804-a61415f53304 · outbound

This paper cites Learning multiple layers of features from tiny images.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Learning multiple layers of features from tiny images

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:29.808530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d74ed9eb-5f3f-40fc-afef-2ee345e90714 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Imagenet: A large-scale hierarchical image database

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:29.908738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0418412e-14cb-4dac-968b-2c8f52c32d34 · outbound

This paper cites The japanese female facial expression (jaffe) dataset.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage The japanese female facial expression (jaffe) dataset

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:06:30.488362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81a4de9a-2217-42f0-92f0-0931fff0d4c4 · outbound

This paper cites Gradient-based learning applied to document recognition.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Gradient-based learning applied to document recognition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:30.065489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da8990c-0cb4-4a0d-b2ba-1c0c96f1222c · outbound

This paper cites Deep residual learning for image recognition.

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage Deep residual learning for image recognition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:30.093990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b733a65-6860-465c-a57f-e5c8ec2af145 · outbound

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

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:06:30.120001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.