DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences | Paper Citation Record

Observation 02985910-24fb-4373-a4ae-ee757d41a99a · outbound

This paper cites an unresolved cited work.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:56:03.143134Z

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 435faf4f-d0ce-41bf-a97e-1bf245add1bd · outbound

This paper cites MSE is a metric used to measure the average squared differences between corresponding pixels of two images.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences MSE is a metric used to measure the average squared differences between corresponding pixels of two images

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.121906Z

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 ea04ac53-6dda-46c6-88bd-3ab99f088590 · outbound

This paper cites Exploiting subtle differences in gradients before and after data removal, the DLG attack reconstructs sensitive data points by comparing gradients from the gl obal model.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Exploiting subtle differences in gradients before and after data removal, the DLG attack reconstructs sensitive data points by comparing gradients from the gl obal model

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.102292Z

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 1af4243e-dfa0-4485-9c45-ab2de5fef67b · outbound

This paper cites Part" subset, corresponding to the retained gradients, while the gradients of the remaining 12 images were forgotten. As the reconstruction progresses, it is observed that the.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Part" subset, corresponding to the retained gradients, while the gradients of the remaining 12 images were forgotten. As the reconstruction progresses, it is observed that the

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T17:56:03.084173Z

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 c2273d8a-e8f4-4cf3-9bf5-c4e6d6af7c59 · outbound

This paper cites Federated conformal predictors for distributed uncertainty quantification,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Federated conformal predictors for distributed uncertainty quantification,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.989738Z

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 e415181d-e01e-4eea-b643-22be44bfd305 · outbound

This paper cites Multimodal Federated Learning via Contrastive Representation Ensemble.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Multimodal Federated Learning via Contrastive Representation Ensemble

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T17:56:02.030115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d892d621-bb26-4ab1-9d5b-f556eba81670 · outbound

This paper cites General data protection regulation (GDPR),.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences General data protection regulation (GDPR),

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.974237Z

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 986f5f43-594a-4b97-9fdc-b3cda668406f · outbound

This paper cites Understanding the scope and impact of the california consumer privacy act of 2018,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Understanding the scope and impact of the california consumer privacy act of 2018,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.955832Z

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 a11683be-29a1-482f-8f9c-d8408ae2d8f6 · outbound

This paper cites Wu et al.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Wu et al

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.245594Z

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 132b755a-743b-4535-9feb-f93d18e35946 · outbound

This paper cites Secure and efficient federated learning with provable performance guarantees via stochastic quantization,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Secure and efficient federated learning with provable performance guarantees via stochastic quantization,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.065636Z

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 a3ed1e71-3f60-4659-8cb9-86f52d7ef76b · outbound

This paper cites Toward secure and verifiable hybrid federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Toward secure and verifiable hybrid federated learning,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.046684Z

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 04b68458-282b-4ff7-afc8-c81892bb2690 · outbound

This paper cites Reliable and interpretable personalized federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Reliable and interpretable personalized federated learning,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.026297Z

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 ce1814bf-4bce-4e7f-958b-63ee920d2a3b · outbound

This paper cites Revisiting weighted aggregation in federated learning with neural networks,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Revisiting weighted aggregation in federated learning with neural networks,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.007143Z

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 ee7b4af2-00c3-4e40-8607-449d1f7cdfc0 · outbound

This paper cites Fedrecovery: Differentially private machine unlearning for federated learning frameworks,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Fedrecovery: Differentially private machine unlearning for federated learning frameworks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.831148Z

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 745eacbb-4fba-47de-924d-c49a22b1055c · outbound

This paper cites Guaranteeing data privacy in federated unlearning with dynamic user participation,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Guaranteeing data privacy in federated unlearning with dynamic user participation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.810394Z

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 66766310-9c99-4b21-b8c8-8968bba89251 · outbound

This paper cites Privacy-preserving federated unlearning with certified client removal,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Privacy-preserving federated unlearning with certified client removal,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.790948Z

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 ad71e60c-62d8-4816-b89e-a232fbca3955 · outbound

This paper cites Federated unlearning and its privacy threats,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Federated unlearning and its privacy threats,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.770566Z

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 24b392ed-0743-4e48-b6c2-d77e953afa78 · outbound

This paper cites Federaser: Enabling efficient client- level data removal from federated learning models,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Federaser: Enabling efficient client- level data removal from federated learning models,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.935008Z

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 34b7a254-f639-4b3d-91b0-6e30b843f4c0 · outbound

This paper cites A survey on federated unlearning: Challenges, methods, and future directions,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences A survey on federated unlearning: Challenges, methods, and future directions,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.910858Z

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 ab91dbc8-3585-4efb-8c0f-29b11f04d229 · outbound

This paper cites In addition, Wang et al.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences In addition, Wang et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.223534Z

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 5387bcee-c2d3-4037-86e8-dbcd3c3794bb · outbound

This paper cites Asynchronous federated unlearning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Asynchronous federated unlearning,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.893888Z

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 4f9a5c5f-df25-4b21-b5f9-ef08bf5c455a · outbound

This paper cites Fast federated machine unlearning with nonlinear functional theory,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Fast federated machine unlearning with nonlinear functional theory,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.876956Z

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 68760636-c262-4109-99f1-b828ff956d98 · outbound

This paper cites Verifi: Towards verifiable federated unlearning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Verifi: Towards verifiable federated unlearning,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.856281Z

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 793c06aa-fdab-4f55-a089-40ecff933035 · outbound

This paper cites iDLG: Improved Deep Leakage from Gradients.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences iDLG: Improved Deep Leakage from Gradients

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T17:56:02.131700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c172fc-7aaf-486e-8bc9-cafc5215303a · outbound

This paper cites Inverting gradients-how easy is it to break privacy in federated learning?,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Inverting gradients-how easy is it to break privacy in federated learning?,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.648811Z

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 59f5164a-abe8-45fb-a9ba-9aa3308b7b57 · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences See through gradients: Image batch recovery via gradinversion,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.628130Z

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 fcc5cba0-0a6e-41cc-bba4-fda6b08e21cc · outbound

This paper cites [28] who combined GAN priors with gradient-free optimizers to bypass existing defenses.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences [28] who combined GAN priors with gradient-free optimizers to bypass existing defenses

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.205792Z

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 06e949d8-fb3a-4f41-a4fb-dc1b12b5c0aa · outbound

This paper cites When federated learning meets privacy -preserving computation,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences When federated learning meets privacy -preserving computation,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.753232Z

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 98791342-7739-4b99-8e3d-fb6e738d119a · outbound

This paper cites [30] proposed a generative gradient inversion framework that eliminates the need for iterative optimization through auxiliary data and feature separation techniques.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences [30] proposed a generative gradient inversion framework that eliminates the need for iterative optimization through auxiliary data and feature separation techniques

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.183970Z

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 88780fcd-1fda-4176-9dc6-450efbc5cc07 · outbound

This paper cites Securing secure aggregation: Mitigating multi- round privacy leakage in federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Securing secure aggregation: Mitigating multi- round privacy leakage in federated learning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.732921Z

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 9cb9f0c4-6cd3-4b70-95cf-7ee729a9123f · outbound

This paper cites Federated Unlearning with Knowledge Distillation.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Federated Unlearning with Knowledge Distillation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:56:02.111172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc2f3fc-b66e-44c6-b885-896e690f505d · outbound

This paper cites Federated unlearning via classdiscriminative pruning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Federated unlearning via classdiscriminative pruning,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.715051Z

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 60c174eb-056c-4b71-8d10-d8cd7d5d38ae · outbound

This paper cites The right to be forgotten in federated learning: An efficient realization with rapid retraining,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences The right to be forgotten in federated learning: An efficient realization with rapid retraining,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.694838Z

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 2366a008-56e3-4938-8413-b12e7ff22d22 · outbound

This paper cites honest-but-curious.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences honest-but-curious

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:03.162515Z

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 d7036c3c-7a24-4463-aeb5-f11c66865149 · outbound

This paper cites Deep leakage from gradients,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Deep leakage from gradients,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.670401Z

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 7615f89b-cee2-4655-8892-00f4adceff7d · outbound

This paper cites Gradient inversion with generative image prior,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Gradient inversion with generative image prior,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.606353Z

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 5bd1e343-2ca8-4f4a-ada6-7e0500d817d1 · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Auditing privacy defenses in federated learning via generative gradient leakage,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.589717Z

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 71cde58c-c783-4747-80fe-8ee04af6e165 · outbound

This paper cites Gifd: A generative gradient inversion method with f eature domain optimization,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Gifd: A generative gradient inversion method with f eature domain optimization,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.566477Z

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 49cbcb4f-c172-4b75-a698-fa11cc1c0689 · outbound

This paper cites Fast generation -based gradient leakage attacks: An approach to generate training data directly from the gradient,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Fast generation -based gradient leakage attacks: An approach to generate training data directly from the gradient,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.546934Z

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 5cb40117-2e0c-4883-9e17-3a08695807c1 · outbound

This paper cites DGGI: Deep Generative Gradient Inversion with diffusion model,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences DGGI: Deep Generative Gradient Inversion with diffusion model,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.525098Z

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 23194cec-9a1f-4d1e-9c73-d7a71c9e4757 · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Secureml: A system for scalable privacy - preserving machine learning,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.496623Z

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 7d43af15-3fdc-4bc5-9592-bc3affc4a7df · outbound

This paper cites QUOTIENT: Two-party secure neural network training and prediction,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences QUOTIENT: Two-party secure neural network training and prediction,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.476154Z

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 3c2c9d3a-6f62-45b1-ac4e-6aa3b31c8073 · outbound

This paper cites Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T17:56:02.189122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579af876-c0f2-4c2f-8ff7-d90eddb21c1b · outbound

This paper cites VerifyNet: Secure and verifiable federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences VerifyNet: Secure and verifiable federated learning,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.460079Z

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 46dcd7a5-f899-4b06-bdd3-58286006db6d · outbound

This paper cites Exploiting unintended feature leakage in collaborative learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Exploiting unintended feature leakage in collaborative learning,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.440175Z

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 742db4e4-fe75-4dfe-a7ff-e5e6717db26a · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Secureml: A system for scalable privacy- preserving machine learning,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.423223Z

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 32512c88-49ef-4f07-9ca8-662973f22cc0 · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Differentially Private Federated Learning: A Client Level Perspective

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T17:56:02.209538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1273b1e5-3026-4cf1-90e7-51d251ab9fc4 · outbound

This paper cites Gradient-leakage resilient federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Gradient-leakage resilient federated learning,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.406634Z

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 49f5d89b-9b03-4105-9f6d-eacf4ba5505c · outbound

This paper cites Preserving data privacy in federated learning through large gradient pruning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Preserving data privacy in federated learning through large gradient pruning,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.390277Z

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 703f02c8-dd2f-48c0-9ca4-d61effa39a01 · outbound

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

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Soteria: Provable defense against privacy leakage in federated learning from representation perspective,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.375466Z

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 7e86ca70-e859-4090-9d99-c823de281d36 · outbound

This paper cites A framework for evaluating client privacy leakages in federated learning,.

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences A framework for evaluating client privacy leakages in federated learning,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:56:02.356189Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers