Paper Citation Record · LEDGER

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

As of 18 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2506.08435.

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

pith.paper-citation-record.v1
2506.08435 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:21:07.900685Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:49:46.693565Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T15:49:47.095252Z

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy47
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 132b2831-d662-49c8-8aea-3bbea1293836 · outbound

This paper cites Federated learning and differential privacy for medical image analysis.Scientific reports, 12(1):1953, 2022.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Federated learning and differential privacy for medical image analysis.Scientific reports, 12(1):1953, 2022

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.934491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 824d0520-0c73-45d6-ad7c-cffb769670ae · outbound

This paper cites A hybrid frame- work for glaucoma detection through federated machine learning and deep learning models.BMC Medical Infor- matics and Decision Making, 24(1):115, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings A hybrid frame- work for glaucoma detection through federated machine learning and deep learning models.BMC Medical Infor- matics and Decision Making, 24(1):115, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.906410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a94d7ca-f6c6-488b-a9fb-94c89d0308fb · outbound

This paper cites Privacy-preserving deep learning via additively homo- morphic encryption.IEEE TIFS, 13(5):1333–1345, 2017.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Privacy-preserving deep learning via additively homo- morphic encryption.IEEE TIFS, 13(5):1333–1345, 2017

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.877193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bf8d38bc-02d4-47c7-8999-752720ab3017 · outbound

This paper cites an unresolved cited work.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:21:09.841885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 85895d3e-c025-4c54-849b-e914a89d16cc · outbound

This paper cites Bartoldson, James Diffenderfer, Konstantinos Parasyris, and Bhavya Kailkhura.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Bartoldson, James Diffenderfer, Konstantinos Parasyris, and Bhavya Kailkhura

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.819918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ae3038c-a7cd-4acf-8c2e-f1b66820a216 · outbound

This paper cites When the curious abandon honesty: Federated learning is not private.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings When the curious abandon honesty: Federated learning is not private

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.796724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 51f59b5c-3a14-4852-b9d2-4dc32e4350ec · outbound

This paper cites Practical secure aggregation for privacy-preserving ma- chine learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Practical secure aggregation for privacy-preserving ma- chine learning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.756324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21ad8c8e-14c2-4cf3-928b-4af29517ab7a · outbound

This paper cites Convex optimization.Cambridge UP, 2004.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Convex optimization.Cambridge UP, 2004

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.721501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1ddc6faa-2fb1-458d-897b-9324c98a28c2 · outbound

This paper cites Extracting training data from large language models.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Extracting training data from large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.689345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e396fb1f-1f7e-429f-aff8-5366799e8cf3 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Quantifying Memorization Across Neural Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.451991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e26cdb-be78-41e0-a4f9-c6196eee2acc · outbound

This paper cites Extract- ing training data from diffusion models.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Extract- ing training data from diffusion models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.642870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4a14afc2-1276-480e-81de-3ce99f11ec74 · outbound

This paper cites Fowl, et al.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Fowl, et al

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.610723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 79f21347-cc1d-4a22-b9d5-0bcfa3c006c5 · outbound

This paper cites Revealing and protecting labels in distributed training.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Revealing and protecting labels in distributed training

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.587690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d493afd7-a1e4-4fe7-ba6e-1f09f6c029cc · outbound

This paper cites Federated learning for predicting clini- cal outcomes in patients with covid-19.Nature medicine, 27(10):1735–1743, 2021.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Federated learning for predicting clini- cal outcomes in patients with covid-19.Nature medicine, 27(10):1735–1743, 2021

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.561974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ef9a326-6c42-4221-9629-f81f56635907 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings An image is worth 16x16 words: Transformers for image recognition at scale

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.529284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fddffd70-e77a-48b9-badd-7c4ce081bbca · outbound

This paper cites SoK: On Gradient Leakage in Federated Learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings SoK: On Gradient Leakage in Federated Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.522312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bbc4dfb-985d-46a4-8a4e-cc5916d66dd2 · outbound

This paper cites The algorithmic foundations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3–4):211– 407, 2014.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings The algorithmic foundations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3–4):211– 407, 2014

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.528581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ea651b7-84c0-4f46-bbff-6ca5898b7a0a · outbound

This paper cites Exploiting pre-trained models and low- frequency preference for cost-effective transfer-based attack.ACM Trans.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Exploiting pre-trained models and low- frequency preference for cost-effective transfer-based attack.ACM Trans

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.482115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a65a9c26-a031-42e8-baaf-d795715a04fb · outbound

This paper cites Guardian: Guarding against gradient leakage with provable de- fense for federated learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Guardian: Guarding against gradient leakage with provable de- fense for federated learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.445070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 82ad1355-48b2-4865-972d-4c29225b75ff · outbound

This paper cites On the trustworthiness landscape of state-of-the-art generative models: A survey and outlook.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings On the trustworthiness landscape of state-of-the-art generative models: A survey and outlook

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.415622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1beb56c3-de7e-427f-ba15-6c5ada9528b5 · outbound

This paper cites Adap dp-fl: Differ- entially private federated learning with adaptive noise.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Adap dp-fl: Differ- entially private federated learning with adaptive noise

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.388212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c99c892-eccc-4f3b-9f0f-4c1cb9d6195d · outbound

This paper cites Inverting gradients-how easy is it to break privacy in federated learning? InNeurIPS, volume 33, pages 16937–16947, 2020.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Inverting gradients-how easy is it to break privacy in federated learning? InNeurIPS, volume 33, pages 16937–16947, 2020

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.364103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d4f64195-8ae1-497a-89bc-b63526b4e08f · outbound

This paper cites Differentially Private Federated Learning: A Client Level Perspective.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Differentially Private Federated Learning: A Client Level Perspective

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.578825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3f3164-1afd-4a51-8474-3a4da049374e · outbound

This paper cites Federated learning for medical image anal- ysis: A survey.Pattern Recognit., 151:110424, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Federated learning for medical image anal- ysis: A survey.Pattern Recognit., 151:110424, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.337575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bc364678-4e49-4b5d-bd57-d0426629806f · outbound

This paper cites Does dif- ferential privacy really protect federated learning from gradient leakage attacks?IEEE Transactions on Mobile Computing, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Does dif- ferential privacy really protect federated learning from gradient leakage attacks?IEEE Transactions on Mobile Computing, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.307723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bc7c7b86-b32f-494c-8940-49e98d80665e · outbound

This paper cites Eval- uating gradient inversion attacks and defenses in feder- ated learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Eval- uating gradient inversion attacks and defenses in feder- ated learning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.265109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e84cd974-34e3-46f9-9909-77615cbc2f05 · outbound

This paper cites Gra- dient inversion with generative image prior.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Gra- dient inversion with generative image prior

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.233924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2bf75c8c-3793-49f2-b04a-e818d50d5c92 · outbound

This paper cites Toward Training at ImageNet Scale with Differential Privacy.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Toward Training at ImageNet Scale with Differential Privacy

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.622647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dd5965e-4ff0-4b33-8cc9-4430a4f4746a · outbound

This paper cites An international study presenting a federated learning ai platform for pediatric brain tumors.Nature communica- tions, 15(1):7615, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings An international study presenting a federated learning ai platform for pediatric brain tumors.Nature communica- tions, 15(1):7615, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.209779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47584a1b-4dae-4350-b212-b4da184e2a01 · outbound

This paper cites On the convergence of fedavg on non-iid data.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings On the convergence of fedavg on non-iid data

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.179053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f4dd3469-15cd-436d-a8b2-147d03cc9145 · outbound

This paper cites Fedbn: Federated learning on non-iid features via local batch normalization.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Fedbn: Federated learning on non-iid features via local batch normalization

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.135431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fe245c1f-f2b2-457a-bdec-6c82cd6fa112 · outbound

This paper cites Auditing privacy defenses in federated learning via gen- erative gradient leakage.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Auditing privacy defenses in federated learning via gen- erative gradient leakage

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.108130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8364c06d-669a-4f15-bc5d-157bca4f5947 · outbound

This paper cites Backdoor defense with machine unlearning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Backdoor defense with machine unlearning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.075164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ccdf2b88-24e3-4295-a6e8-3a58d50257f4 · outbound

This paper cites Pre- dicting treatment response in multicenter non-small cell lung cancer patients based on federated learning.BMC cancer, 24(1):688, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Pre- dicting treatment response in multicenter non-small cell lung cancer patients based on federated learning.BMC cancer, 24(1):688, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.038892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f0f3f96-f468-46b3-a4fd-441c6226e8cc · outbound

This paper cites SGDR: stochastic gradient descent with warm restarts.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings SGDR: stochastic gradient descent with warm restarts

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:09.013707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 377071ac-48b0-413a-8996-3780cf0682c5 · outbound

This paper cites A tutorial on fisher information.Journal of Mathemati- cal Psychology, 80:40–55, 2017.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings A tutorial on fisher information.Journal of Mathemati- cal Psychology, 80:40–55, 2017

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.987624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a99f17a-e1bd-4e5b-a4f8-e5bf8d3ffe53 · outbound

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

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Instance-wise batch label restoration via gradients in federated learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.951107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1a00360c-fd57-4c4c-b76e-f25c4c25b1cb · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Towards deep learning models resistant to adversarial attacks

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.921003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 189fcdb1-ae2b-4b0c-9779-765b4ba71463 · outbound

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

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Communication-efficient learning of deep networks from decentralized data

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.878843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 942e7c29-210a-4d1f-a2a7-a8b32b35a4d3 · outbound

This paper cites Transforming large-size to lightweight deep neural networks for iot applications.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Transforming large-size to lightweight deep neural networks for iot applications

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.846426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38436d76-4951-43eb-86ad-2ecddc1a4aac · outbound

This paper cites Secureml: A system for scalable privacy-preserving machine learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Secureml: A system for scalable privacy-preserving machine learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.819035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 088f02c1-8cb6-483c-9e40-06ee58918bdb · outbound

This paper cites Nguyen, Ming Ding, Pubudu N.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Nguyen, Ming Ding, Pubudu N

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.787150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4ab9c0a-53ba-471c-9198-c38320c3d966 · outbound

This paper cites Eluding secure aggregation in federated learning via model inconsistency.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Eluding secure aggregation in federated learning via model inconsistency

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.755629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6d550a7f-83fb-4f64-be11-7f9f708fcbae · outbound

This paper cites A survey on deep learning: Algorithms, techniques, and applica- tions.ACM computing surveys, 51(5):1–36, 2018.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings A survey on deep learning: Algorithms, techniques, and applica- tions.ACM computing surveys, 51(5):1–36, 2018

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.723054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 422902f2-b10d-43ae-a303-6cbf20a0ad00 · outbound

This paper cites Federated learning in medicine: facil- itating multi-institutional collaborations without sharing patient data.Scientific reports, 10(1):12598, 2020.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Federated learning in medicine: facil- itating multi-institutional collaborations without sharing patient data.Scientific reports, 10(1):12598, 2020

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.688321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 90172792-a91e-4a35-b7e4-517c335f813f · outbound

This paper cites Soteria: Provable defense against privacy leakage in federated learning from representation perspective.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Soteria: Provable defense against privacy leakage in federated learning from representation perspective

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.650122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7fe7c36-806a-441f-b768-2cc4b58c59cc · outbound

This paper cites More than enough is too much: Adaptive defenses against gradient leakage in production federated learning.IEEE/ACM Transactions on Networking, 32(4):3061–3075, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings More than enough is too much: Adaptive defenses against gradient leakage in production federated learning.IEEE/ACM Transactions on Networking, 32(4):3061–3075, 2024

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.785834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15185ed2-6d2e-4188-82d2-ebac4c5c6efb · outbound

This paper cites Pro- tect privacy from gradient leakage attack in federated learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Pro- tect privacy from gradient leakage attack in federated learning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.622107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 04aa43cb-d45a-4068-a46d-b0f49ef829fb · outbound

This paper cites Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.807147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77037d7f-d0e3-4f4a-816e-9d058f04dc37 · outbound

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

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.818791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c536d06c-e135-4095-8fa6-77b42e77f8f8 · outbound

This paper cites Fishing for user data in large-batch federated learning via gradient magnification.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Fishing for user data in large-batch federated learning via gradient magnification

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.590070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c65b002a-bddc-45a1-9d6f-3975b4e4c5f5 · outbound

This paper cites See through gradients: Image batch recovery via gradinver- sion.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings See through gradients: Image batch recovery via gradinver- sion

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.560646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ead6bad-755b-4fc2-a2d1-3a61d12735a5 · outbound

This paper cites Gradient obfuscation gives a false sense of security in federated learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Gradient obfuscation gives a false sense of security in federated learning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.534078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6a9cf947-30a4-44fa-a940-7670dde65541 · outbound

This paper cites BatchCrypt: Efficient homomorphic encryption for Cross-Silo federated learning.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings BatchCrypt: Efficient homomorphic encryption for Cross-Silo federated learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.494231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a633855e-9a40-4c30-97af-1230c5350be3 · outbound

This paper cites Re- cent methodological advances in federated learning for healthcare.Patterns, 5(6):101006, 2024.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Re- cent methodological advances in federated learning for healthcare.Patterns, 5(6):101006, 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.450609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5d98bd3f-28a8-4af1-a2fa-5b5867e4f17f · outbound

This paper cites iDLG: Improved Deep Leakage from Gradients.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings iDLG: Improved Deep Leakage from Gradients

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:07.883060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35eab061-2342-4ce5-8e68-4b5c2b0cd79b · outbound

This paper cites Zhao, Atul Sharma, Ahmed Roushdy Elko- rdy, et al.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings Zhao, Atul Sharma, Ahmed Roushdy Elko- rdy, et al

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:08.418465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 734a47e1-689b-409f-a1e1-25e4910b9c1a · outbound

This paper cites specific/common parameters.

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings specific/common parameters

Reference 58

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T05:21:08.379623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 4e256c42-a149-4f88-8b3f-75b6380f2958 · inbound

Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning cites this paper.

Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:49:47.100839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.