Pith. sign in

Paper Citation Record · LEDGER

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation

As of 10 August 2026, this Paper Citation Record lists 100 of 135 outbound references and 1 inbound Pith citation observation for arXiv:2506.19360.

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

pith.paper-citation-record.v1
2506.19360 v2

Coverage vector

measured 100 of 135 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:12:17.157633Z

measured 101 of 101 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-14T21:10:36.000486Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-14T21:18:00.144058Z

Reference resolution

100 of 135 outbound references displayed

  • verified exact9
  • verified fuzzy3
  • unresolved88
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 89d37537-98c7-465b-b063-0a8792890f6e · outbound

This paper cites Deep learning with differential privacy.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Deep learning with differential privacy

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.764637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.764637Z digest=sha256:8741e817906f1c8ba378b0c1a5d78b4fd7ce50fe3d897a2071fba10280a09917

Observation d1386841-bf6f-4f2f-b075-c9bdd6b57eb6 · outbound

This paper cites Big healthcare data: preserving secu- rity and privacy.Journal of big data, 5(1):1–18, 2018.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Big healthcare data: preserving secu- rity and privacy.Journal of big data, 5(1):1–18, 2018

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.769670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.769670Z digest=sha256:f916e51e4423081c395598f5d05fe55a897ae15a02a3ad08d851098f03f796d9

Observation 1b3c5248-763b-47f7-a327-fc8c11133734 · outbound

This paper cites Evaluations of Machine Learning Privacy Defenses are Misleading.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Evaluations of Machine Learning Privacy Defenses are Misleading

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.885361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.774111Z digest=sha256:89d46206a736110eb347b784e83f5f6569d8dd009f5149361ee2e587713ad76d

Observation 9cc63707-d08a-44ff-9585-111424626013 · outbound

This paper cites Wasserstein gan, 2017.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Wasserstein gan, 2017

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.778894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.778894Z digest=sha256:248b1142884e5b0fe7928701f8b7f7ce844f8919f31b5d941b7310702f7e2f3a

Observation f41295a2-7a26-4092-88b0-7623c5482608 · outbound

This paper cites Feedback-guided data synthesis for imbal- anced classification.arXiv e-prints, pages arXiv–2310, 2023.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Feedback-guided data synthesis for imbal- anced classification.arXiv e-prints, pages arXiv–2310, 2023

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.782929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.782929Z digest=sha256:03cf73265d38ef07224d7be964f8141b543bcefd6e6726f0dc13238cf01022f9

Observation 47646c47-9473-4b56-bc35-15254a0143f4 · outbound

This paper cites Automatic Discovery of Privacy-Utility Pareto Fronts.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Automatic Discovery of Privacy-Utility Pareto Fronts

Reference 6

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.871750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.786843Z digest=sha256:21bcd0eedaed9dee70252b83d408a3cb4910e798f0058bea85afd1a2c26fd521

Observation c7c96911-2d93-401a-a881-0fe0b46bf0d9 · outbound

This paper cites Synthetic Data from Diffusion Models Improves ImageNet Classification.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Synthetic Data from Diffusion Models Improves ImageNet Classification

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.791229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.791229Z digest=sha256:643e6c72d8fea0c8027615870186cb7c6e5e57d6eba9d3c60bb769e45d9edf1e

Observation 02e8642f-1236-49c6-8971-85efb472448b · outbound

This paper cites Differential privacy has disparate impact on model accuracy.Advances in neural information processing systems, 32, 2019.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Differential privacy has disparate impact on model accuracy.Advances in neural information processing systems, 32, 2019

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.795354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.795354Z digest=sha256:a6fb21a332ab6413fa6f1c92cfcd07aa866cf1ad965b8c8c38e8b8cc0508d97e

Observation b84477ab-ff64-4428-b6b1-5bd82d927ac0 · outbound

This paper cites Leaving Reality to Imagination: Robust Classification via Generated Datasets.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Leaving Reality to Imagination: Robust Classification via Generated Datasets

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.849438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.799204Z digest=sha256:23f82db38a1922bbf8043f3255f09265650f0b752ddb86c6e8c2cb7fd28c0de4

Observation 04339a51-06e0-458c-9416-1513a43d58e3 · outbound

This paper cites Conditional Image Generation with Score-Based Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Conditional Image Generation with Score-Based Diffusion Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.802988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.802988Z digest=sha256:ff9993247889344fd0b423cf0b9148d8b7fccd656e1cc1346c64358aa8eb95b9

Observation a38a2a2e-acf9-429b-b9bb-aaea207a986d · outbound

This paper cites Privacy in Social Media: Identification, Mitigation and Applications.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Privacy in Social Media: Identification, Mitigation and Applications

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.807160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.807160Z digest=sha256:b34be9106176603bd7cfe6f8c6e08549723057f74b3c07a3540895e45f1b849c

Observation 66e9a5db-47d1-430b-bd2c-ec6e41cb6648 · outbound

This paper cites Private GANs, Revisited.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Private GANs, Revisited

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.811786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.811786Z digest=sha256:a7242fa4f476dde471ac07901833803fa794c9c86deada918958fd0f6cf99651

Observation b0ff5968-3f05-4a5a-8685-5ef33f036e92 · outbound

This paper cites Large Scale GAN Training for High Fidelity Natural Image Synthesis.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Large Scale GAN Training for High Fidelity Natural Image Synthesis

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.815967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.815967Z digest=sha256:76a3e1e026fa709b272248d7ef1ade695ff88adb106fd2bf6998b6f0dc6d340e

Observation 50a6fff5-2863-4078-afd3-f16e3ebe052e · outbound

This paper cites Instructpix2pix: Learning to follow image editing in- structions.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Instructpix2pix: Learning to follow image editing in- structions

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.819729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.819729Z digest=sha256:a9595e5246a96c3166afbecaa9b5c0cde9da52392eeba6efb198735f85b97269

Observation 342413ad-9f95-4858-bcd1-bb63cc01afe4 · outbound

This paper cites Don’t generate me: Training differen- tially private generative models with sinkhorn diver- gence.Advances in Neural Information Processing Systems, 34:12480–12492, 2021.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Don’t generate me: Training differen- tially private generative models with sinkhorn diver- gence.Advances in Neural Information Processing Systems, 34:12480–12492, 2021

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.823666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.823666Z digest=sha256:d555fb6a087954e2685ee23fcf9cf623223331919e14084cbb6fc7d428658f2e

Observation fa996c9e-c958-417c-bd99-26a61f6fd044 · outbound

This paper cites Member- ship inference attacks from first principles.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Member- ship inference attacks from first principles

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.829477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.829477Z digest=sha256:3db2838fdd0b67f928d82c2f83b89dbaaa4a266c52ad096c23c177228f3e8098

Observation ff29b0e9-6fcc-4464-8881-0d1de34ea30a · outbound

This paper cites Dataset distil- lation by matching training trajectories.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dataset distil- lation by matching training trajectories

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.832890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.832890Z digest=sha256:8c66c235a28f9c9aa810a4422dde1586c37ece131de674167ec35ef7c90edb81

Observation 7426592f-d395-442c-b463-3154c71b3052 · outbound

This paper cites Gs-wgan: A gradient-sanitized approach for learning differentially private generators.Advances in Neural Information Processing Systems, 33:12673– 12684, 2020.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Gs-wgan: A gradient-sanitized approach for learning differentially private generators.Advances in Neural Information Processing Systems, 33:12673– 12684, 2020

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.837107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.837107Z digest=sha256:0f482a8373339b4d6c01e0a4b8028de693491c14274835814bc973b71a3d5f5f

Observation 82ee82de-d46d-48fd-9df7-f7ce76bedb31 · outbound

This paper cites Gan-leaks: A taxonomy of membership inference at- tacks against generative models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Gan-leaks: A taxonomy of membership inference at- tacks against generative models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.840634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.840634Z digest=sha256:75bdc98a6fb00a531d0a6a1af8cf395525329090a0d8686d178bee4798010fa2

Observation b6c74020-e01e-46a5-9cbf-0cc7d515a1a7 · outbound

This paper cites Dpgen: Differentially private generative energy-guided network for natural image synthesis.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dpgen: Differentially private generative energy-guided network for natural image synthesis

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.844304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.844304Z digest=sha256:81ab2e05b7e906a68bef3a118ceb0ca04a680751817154c9005f6087205f663e

Observation 0549d354-f7d7-4f46-b602-d7a5ea4f7392 · outbound

This paper cites Variational Lossy Autoencoder.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Variational Lossy Autoencoder

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.848502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.848502Z digest=sha256:b40ad6f1919abfafb45a008815a3dc7bf9f45d53a7e11747e3e051902b8289b7

Observation dad4e1d9-89d1-4636-b8e9-6a6c3911c8e5 · outbound

This paper cites Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.852350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.852350Z digest=sha256:8b3bc2d78654d168c9dc42c08424e50656c67d09c9e96291627aaf75d63c013b

Observation 4d414046-3f3a-4b17-86ad-48e5536c2fda · outbound

This paper cites Label-only membership inference attacks.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Label-only membership inference attacks

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.855827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.855827Z digest=sha256:4557e4166e4bbf18366f15a602b6a3ff2377a30d3540e0a7832f2bf47b09ff1f

Observation 2ea2ffd0-c9ae-43cf-bd6f-7a699fbca190 · outbound

This paper cites On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models

Reference 24

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.782904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.860027Z digest=sha256:08743563a0c85e0f740f09c61e20c194699e0dddb69892a7707741f90c49c54f

Observation 50bd7bd5-2f4a-4e27-b3d9-d15dc2a2f617 · outbound

This paper cites End- to-end sinkhorn autoencoder with noise generator.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation End- to-end sinkhorn autoencoder with noise generator

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.863460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.863460Z digest=sha256:3bd025860335465506ade852c95081f36cb49f90cb05850918bec8d28b31b129

Observation ccd24067-9cb1-4082-a384-bdd0c64d3203 · outbound

This paper cites Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.866922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.866922Z digest=sha256:24cf6b62019bfbcd005712f4f81b2c5ee2b513ff1507766574f50609aca722f5

Observation 624238ec-8d6f-4c84-adf5-fec94b8d82f7 · outbound

This paper cites Differentially Private Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Differentially Private Diffusion Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.870115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.870115Z digest=sha256:73f39f3b75f7f3077c50ab9da4bfd77114bda92e64fa26efd63bca99991184f5

Observation a5a086b2-8bd0-4bd2-9917-9679b2c11cde · outbound

This paper cites Are diffusion models vulnerable to membership inference attacks? InInternational Conference on Machine Learning, pages 8717–8730.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Are diffusion models vulnerable to membership inference attacks? InInternational Conference on Machine Learning, pages 8717–8730

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.873862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.873862Z digest=sha256:6d8f95b1641e24bfe3911c8e81ab8ffbb241791b0e3938c1dd48e8b23406701c

Observation 367ab0c8-0b73-4777-8870-b7b8c0331b84 · outbound

This paper cites an unresolved cited work.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.877694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.877694Z digest=sha256:0dc7448881f2f483bef47aecad8d49666600299450d969de779adc22aea3dbc8

Observation adfb1bf0-cbf8-4166-9b6e-ed34958b8e12 · outbound

This paper cites Calibrating noise to sensitivity in pri- vate data analysis.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Calibrating noise to sensitivity in pri- vate data analysis

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.881543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.881543Z digest=sha256:78b0e3e782eb05354cd34012b2da13579a31313c971241223cff05a36f2acec4

Observation 76bb79f6-939b-48cc-987a-36fbd34ed4ae · outbound

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

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation The algorithmic foundations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3–4):211– 407, 2014

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.885242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.885242Z digest=sha256:0fe50c5ef91fbb3abad956959fce97f5e002d6541820ee414a206cf5d8031e06

Observation c17542ac-93b7-483a-a9f0-aeee8928cd75 · outbound

This paper cites Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models

Reference 32

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.760719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.889072Z digest=sha256:11ba60911a025b99931c93119411292b3ad540ca82ba6d49dc614ca28aeee897

Observation c1bfc092-d471-4a67-9ec8-e5ecd059db9b · outbound

This paper cites Privacy-preserving data publishing: A survey of recent developments.ACM Computing Surveys (Csur), 42(4):1–53, 2010.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Privacy-preserving data publishing: A survey of recent developments.ACM Computing Surveys (Csur), 42(4):1–53, 2010

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.893573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.893573Z digest=sha256:99d08096b1968b4715a93b86a554c55c1ba445943b1217ec0c7b247a5fbdefd6

Observation 10ba2729-41dd-4fb9-96dc-8fb906e13970 · outbound

This paper cites An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.897629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.897629Z digest=sha256:2f0614f3cf2a3c9b9265fc6588ce3e83cd0296c8b2bc4d93423e5e8c47455816

Observation e1a3ff5b-3085-40d1-8e5c-747d20438888 · 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.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Inverting gradients-how easy is it to break privacy in federated learning?Advances in neural information processing systems, 33:16937– 16947, 2020

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.901409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.901409Z digest=sha256:b3206068ffa2ed1b6f3a1db1509d784b8009ada0cad273b4dcb9c109eb42f386

Observation 967ed56c-b20c-4d22-ae24-797eacadcda3 · outbound

This paper cites Learning generative models with sinkhorn divergences.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Learning generative models with sinkhorn divergences

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.905220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.905220Z digest=sha256:5b3b12b06465e85d87de506c22dd5e1e2c7f021584ad56fd6d99303d56e4cd6b

Observation b3feecb2-1cac-431f-973f-edae722a5dfb · outbound

This paper cites Differentially Private Diffusion Models Generate Useful Synthetic Images.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Differentially Private Diffusion Models Generate Useful Synthetic Images

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.909245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.909245Z digest=sha256:b97556d1434685ceec378043c05d4e136950c92b9d1f46c73ebb290813bb4d07

Observation 48c03686-1bed-44ae-92e2-fac781172f1e · outbound

This paper cites Generative adversar- ial nets.Advances in neural information processing systems, 27, 2014.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Generative adversar- ial nets.Advances in neural information processing systems, 27, 2014

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.913370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.913370Z digest=sha256:5efe963d6521959444bb6faba57f3d798a054d6a2a30d73f3fbfa58ca7af80cb

Observation 634f262d-2db2-48f5-ae75-5a3cf7015649 · outbound

This paper cites Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.917335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.917335Z digest=sha256:36eb4d8457a617c7d7031663b2499c35e58c0e2dae317d83fa18e07260e65910

Observation 33f95a83-fea2-427f-bc46-2c2bf0bd347e · outbound

This paper cites Dp-merf: Differentially private mean em- beddings with randomfeatures for practical privacy- preserving data generation.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dp-merf: Differentially private mean em- beddings with randomfeatures for practical privacy- preserving data generation

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.921670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.921670Z digest=sha256:ec7a7c3c3fc325f2754257b11452e2e253806247df46755a31f4ad2e7d384cfa

Observation 65501f7e-58a8-4199-80d7-1e8b54f463ef · outbound

This paper cites LOGAN: Membership Inference Attacks Against Generative Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation LOGAN: Membership Inference Attacks Against Generative Models

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.926647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.926647Z digest=sha256:d437c17e7371b94cce0f0fca9bf0f0dc9190c2410223e0620e87cc2b1e24f45c

Observation f12becd5-2a12-452d-b2f9-b7b5de9ce869 · outbound

This paper cites Is synthetic data from generative models ready for image recognition?.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Is synthetic data from generative models ready for image recognition?

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.931612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.931612Z digest=sha256:d1b1e192b33768d63c76b35255590c8bc5a79bc3db08e5021083fb2d75f3c168

Observation f72bed62-8368-4e17-974a-9e970b687e99 · outbound

This paper cites Prompt-to-Prompt Image Editing with Cross Attention Control.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Prompt-to-Prompt Image Editing with Cross Attention Control

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.935431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.935431Z digest=sha256:659a32576afb69f4b1f84f120d2efe17a245cc00d423a08ae83bb54ccc415f9d

Observation 8627ef07-3c22-4b09-a4e2-c5276392475a · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.938970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.938970Z digest=sha256:3d6bdf1aea1e3f8e99cf19726bf697062748156f4ffc381b80108e9ce9f3bafd

Observation 6159bb15-a7d5-412b-8763-9736b37d1a36 · outbound

This paper cites Monte carlo and reconstruction membership inference attacks against generative models.Proceed- ings on Privacy Enhancing Technologies, 2019.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Monte carlo and reconstruction membership inference attacks against generative models.Proceed- ings on Privacy Enhancing Technologies, 2019

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.943102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.943102Z digest=sha256:706a9f2b718918063a9b65c9412a83496f92f8f25a43baca541c4c9fde36bfd7

Observation dc85379e-55b3-46a9-806e-d7f72b274f33 · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.946681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.946681Z digest=sha256:d1e890cf6ffe9d2a3b6dfba5eda6e6fe32853868bee6cee11a32510df454829e

Observation 5636b208-b325-4765-abe8-139ec78802a8 · outbound

This paper cites Cas- caded diffusion models for high fidelity image genera- tion.Journal of Machine Learning Research, 23(47):1– 33, 2022.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Cas- caded diffusion models for high fidelity image genera- tion.Journal of Machine Learning Research, 23(47):1– 33, 2022

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.949811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.949811Z digest=sha256:70b3497155ae950368bb1b9a09f82f7957a78245db356d6d7d7a163eb8181f60

Observation e5c3feac-8703-48d4-9295-29bd01027d06 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation LoRA: Low-Rank Adaptation of Large Language Models

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.954190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.954190Z digest=sha256:96ed114ff953891657490629b92e0ba37c2a1410f851643ba93009c05e431079

Observation 33928757-0589-4229-8ae9-183735a84695 · outbound

This paper cites Membership Inference of Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Membership Inference of Diffusion Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.958198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.958198Z digest=sha256:b17809ca04c9c5cf83ff54e26312762f7a7d041b154ab627cf5a2660eefc7328

Observation 5ea591d7-db76-4f1a-9af1-f799e3f69d09 · outbound

This paper cites Membership in- ference attacks on machine learning: A survey.ACM Computing Surveys (CSUR), 54(11s):1–37, 2022.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Membership in- ference attacks on machine learning: A survey.ACM Computing Surveys (CSUR), 54(11s):1–37, 2022

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.961963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.961963Z digest=sha256:e2b83feb24bdc21d526b04069fbfe861ff3396ea544d0ecd908e756c5673c0dd

Observation 6f94c15a-d883-4363-a868-ef022959faa0 · outbound

This paper cites Sok: Privacy- preserving data synthesis.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Sok: Privacy- preserving data synthesis

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.965406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.965406Z digest=sha256:3fd292ba3d7499f2c4e61ff541bcfde210981e0d80d6f7cfef6ad5aae2d304a5

Observation 6318102a-78d7-452e-8dfd-fcfa943eca7f · outbound

This paper cites Chexpert: A large chest radiograph dataset with uncer- tainty labels and expert comparison.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Chexpert: A large chest radiograph dataset with uncer- tainty labels and expert comparison

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.968873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.968873Z digest=sha256:f4ee35528450edaf3b563dfdfd523df6872fe2fb400728bdcd0ee5c1a2432ee2

Observation c7b047fd-8bb7-41ff-b60f-c4287659404b · outbound

This paper cites Provable Membership Inference Privacy.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Provable Membership Inference Privacy

Reference 53

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.682873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.972129Z digest=sha256:237e4f0e5c883c839dacc3385fc34a35c4ca97d9d50b02a35c62873ee053a22b

Observation 57e712db-6805-410f-9266-bd6321dbf6bb · outbound

This paper cites MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members

Reference 54

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.668279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.976474Z digest=sha256:02ca8e5ac7c94c62f534cf2e7892262ac3a6e20b7360e40642bf588e706408b1

Observation 40d8bc9b-4522-42f2-b3db-07877afe8403 · outbound

This paper cites Evaluating differ- entially private machine learning in practice.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Evaluating differ- entially private machine learning in practice

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.980789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.980789Z digest=sha256:c047621d9909f3e9307b318745de2b5385ff21ecf925f6da52d8fe6ab6a3c9df

Observation 93a479c3-702d-4e92-82b7-34dbe04754ba · outbound

This paper cites DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders

Reference 56

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.655084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:16.985233Z digest=sha256:c41eeb41e8afbd0195f5000f4b1ef9bb019187ec8ec95bec79d5b00231d23bec

Observation b3165eef-b6a3-47de-8599-9fe896db296d · outbound

This paper cites Progressive Growing of GANs for Improved Quality, Stability, and Variation.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Progressive Growing of GANs for Improved Quality, Stability, and Variation

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.989491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.989491Z digest=sha256:c8b38549dfa071aeebe2ffd40f6cbd1e94cd340f23c47e0e84b1618aba15fe05

Observation 73e59ad3-4e6a-430b-8e62-077532cab71a · outbound

This paper cites Training gener- ative adversarial networks with limited data.Advances in neural information processing systems, 33:12104– 12114, 2020.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Training gener- ative adversarial networks with limited data.Advances in neural information processing systems, 33:12104– 12114, 2020

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.993196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.993196Z digest=sha256:f32d82fe9bd53db9884deef979a8ad26f310c1b729bd203cc491868dbcc8344c

Observation d9266805-238d-4425-abf1-ac0e49b842f4 · outbound

This paper cites Analyzing and improving the image quality of stylegan.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Analyzing and improving the image quality of stylegan

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:16.996933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:16.996933Z digest=sha256:33fff82c5b1fbb0e83e8c5972b31a79ac7ee224cf0d2267192cf10364b758b9f

Observation ffd792fa-b6b5-418a-a641-bca9812144f0 · outbound

This paper cites Imagic: Text-based real image editing with dif- fusion models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Imagic: Text-based real image editing with dif- fusion models

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.000365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.000365Z digest=sha256:7c5982531b8abff567ae0b9d7683921007c0e2b64ec26fd99120674f5dd6d22e

Observation 5673020f-4f97-494b-81f1-0d58834d718c · outbound

This paper cites When does data augmentation help with membership inference attacks? InInternational conference on machine learn- ing, pages 5345–5355.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation When does data augmentation help with membership inference attacks? InInternational conference on machine learn- ing, pages 5345–5355

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.003702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.003702Z digest=sha256:0485e63ed29dd17089de3f119073d4cf871a8a87f8b9dd2eebd21b9731989144

Observation ce1ef253-97be-41fb-812d-3865cff5573c · outbound

This paper cites Privacy-preserving artificial intelligence in healthcare: Techniques and applications.Computers in Biology and Medicine, 158:106848, 2023.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Privacy-preserving artificial intelligence in healthcare: Techniques and applications.Computers in Biology and Medicine, 158:106848, 2023

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.008041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.008041Z digest=sha256:e54692860aadb43942da38dcf24c2ad37d6f578736043364491358643352f2ba

Observation f5bd0d0a-f62c-4429-a7da-9aa45dea1a10 · outbound

This paper cites Auto-Encoding Variational Bayes.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Auto-Encoding Variational Bayes

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.011390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.011390Z digest=sha256:19e93f75e787a8c6ddf1f68f9072b0b7780094164b4d18d6714083621bab0fd7

Observation a3abfbd5-4183-493e-8247-a0b88cd088ad · outbound

This paper cites An ef- ficient membership inference attack for the diffusion model by proximal initialization.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation An ef- ficient membership inference attack for the diffusion model by proximal initialization

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.015902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.015902Z digest=sha256:89685f09b5b10329d040eeee9aae0137e5a85cca517da7d44553d560b7c06f2b

Observation d42b7a00-8343-4d73-bcc8-ad6bdaaf6793 · outbound

This paper cites Deep learning for medical image cryptography: A compre- hensive review.Applied Sciences, 13(14):8295, 2023.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Deep learning for medical image cryptography: A compre- hensive review.Applied Sciences, 13(14):8295, 2023

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.019799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.019799Z digest=sha256:20c76d392d87b4ba7963e66a75599b497526fb77e081ecfc9c2bb75dbf07ab2c

Observation 9a497479-020c-4580-874a-3b15c8bf33b7 · outbound

This paper cites SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.023902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.023902Z digest=sha256:f8c0a66bc33deeb889a0abbace798e8c1daf977334954215bbe02303db1865e7

Observation abe8d60c-347b-40cb-85a9-c37943981b42 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language mod- els.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language mod- els

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.028306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.028306Z digest=sha256:841fca5010b1b0b24bd3dd2f5cc850d9cbdd7477ab78db251e21b4061806a8ce

Observation f428ed45-81b2-49c2-a92d-45f751f24bb2 · outbound

This paper cites Exploring the benefits of visual prompting in differential privacy.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Exploring the benefits of visual prompting in differential privacy

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.032230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.032230Z digest=sha256:0e193f282ef640707e56c3af9800db52e8d7d90445f216dc8a96b51981c19a18

Observation d56859bf-808f-4ee0-a436-4cadf82880c9 · outbound

This paper cites Deep learning face attributes in the wild.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Deep learning face attributes in the wild

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.036621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.036621Z digest=sha256:4a4877720068191b0ba017a27212dfb8d69a95d2e2abb4379805af2969d2a09f

Observation d6e9a421-3dda-4699-8210-eb4a7e51535d · outbound

This paper cites G- pate: Scalable differentially private data generator via private aggregation of teacher discriminators.Ad- vances in Neural Information Processing Systems, 34:2965–2977, 2021.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation G- pate: Scalable differentially private data generator via private aggregation of teacher discriminators.Ad- vances in Neural Information Processing Systems, 34:2965–2977, 2021

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.040552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.040552Z digest=sha256:bedbb66458fa3a2116aa19242d1cad63103a264ce38259603ceb5ca14997c7e3

Observation bca28483-3037-4911-a24b-4c2487a04c72 · outbound

This paper cites Repaint: Inpainting using denoising diffusion probabilistic mod- els, 2022.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Repaint: Inpainting using denoising diffusion probabilistic mod- els, 2022

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.044026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.044026Z digest=sha256:63d94b04e464d5326d9446c6a38a43d4f57b4e05729d6c5158496c1722314b3b

Observation 29acdc6f-f0c8-410a-8a97-c7c45af4c3fb · outbound

This paper cites Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.048041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.048041Z digest=sha256:e231f8710336e56801f579c588cfbc96d464cbfa4c040a7d3d7d437124d254da

Observation a1b2cf05-69c3-4cc1-aee1-c23a2fad6ae0 · outbound

This paper cites DP-LDMs: Differentially Private Latent Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation DP-LDMs: Differentially Private Latent Diffusion Models

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.051778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.051778Z digest=sha256:21f14eeb1ddb88711e9923c49d124e373b965b281e90fc8553c3ac74e65c1ec9

Observation 53da0ee9-8249-4e99-8c75-0b481fb4e6ab · outbound

This paper cites Membership inference attacks against diffusion mod- els.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Membership inference attacks against diffusion mod- els

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.055522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.055522Z digest=sha256:460b3ee95f7e5aebde1eb0d081c5d6d81d3269ed2c63af33e9ce960e4eea1754

Observation 0533e0bc-b693-4cae-bc05-fa74db5245ad · outbound

This paper cites Exploiting unintended feature leakage in collaborative learning.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Exploiting unintended feature leakage in collaborative learning

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.059658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.059658Z digest=sha256:476132cba44afd0a70f472e4e3f62f7cbd733b8705e2ac1c0a7c2ee85846280f

Observation d0bbc068-416a-4eeb-b259-9104b793f2b4 · outbound

This paper cites SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.063266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.063266Z digest=sha256:4414285bb63cbaa71ff0af6a8360145e7cec24c32f6f59b899f6906d9f489eda

Observation c244a090-dbdb-4cf5-8a7a-321be2b7788b · outbound

This paper cites Conditional Generative Adversarial Nets.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Conditional Generative Adversarial Nets

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.066474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.066474Z digest=sha256:74c3d8b2201e9052a5284c3b1df54d15ddff8da9b90db3ef954b5dabe00e0a56

Observation 13ac35a3-8d1e-4373-a470-58d33906cb12 · outbound

This paper cites Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.070094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.070094Z digest=sha256:db927df967ff7d941df65ac166b29ccb082b1cfa72cd9e2784b0df9ebb8be650

Observation ce7a5d85-41d4-4035-9bb6-ad054e2e3179 · outbound

This paper cites Null-text inversion for editing real images using guided diffusion models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Null-text inversion for editing real images using guided diffusion models

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.074127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.074127Z digest=sha256:eb953d8444b66e19244418ee3eb048b3e607896b59a6f5ed330a94a5db078cc4

Observation 27dbb143-1b82-4a0e-b24d-baabcae95729 · outbound

This paper cites Ma- chine learning with membership privacy using adver- sarial regularization.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Ma- chine learning with membership privacy using adver- sarial regularization

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.077800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.077800Z digest=sha256:edd01d639fec449969de37ff8c99498b33f1428ca0c42bb14506bb147f41d9fe

Observation 69b9664a-0307-4658-b4f3-7af5751bc953 · outbound

This paper cites Com- prehensive privacy analysis of deep learning: Passive and active white-box inference attacks against central- ized and federated learning.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Com- prehensive privacy analysis of deep learning: Passive and active white-box inference attacks against central- ized and federated learning

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.081544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.081544Z digest=sha256:6faaa3417b71f69fb97eee452c43cec8c160a66cb38abf7263784c145ef92a81

Observation 18fc79ed-0299-454a-92d0-e893d5307dd4 · outbound

This paper cites Dataset Meta-Learning from Kernel Ridge-Regression.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dataset Meta-Learning from Kernel Ridge-Regression

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.085681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.085681Z digest=sha256:5202ec30a5e0bec29a2200216e4d90293ca7ad6c01a1c490569fba014485f831

Observation b13e5a4b-e371-4598-9dd6-0cd97c4e7c94 · outbound

This paper cites Dataset distillation with infinitely wide convolutional networks.Advances in Neural Informa- tion Processing Systems, 34:5186–5198, 2021.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dataset distillation with infinitely wide convolutional networks.Advances in Neural Informa- tion Processing Systems, 34:5186–5198, 2021

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.089964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.089964Z digest=sha256:af439527cd1f6479d6ebff8614845508eb5767b60d5cca0e0a44efebd8c5f86f

Observation f3eda1a6-7b2b-45d0-9a97-8e9a1cc912e9 · outbound

This paper cites SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

Reference 84

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:12:17.552610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:17.093813Z digest=sha256:2bd46eb52380392171ce5068625bb91f7cf7fecfcf3a23805baa384abac966c7

Observation 495c693b-4cd1-44c2-94b1-602aa56a90a8 · outbound

This paper cites Black-box Membership Inference Attacks against Fine-tuned Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Black-box Membership Inference Attacks against Fine-tuned Diffusion Models

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.097590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.097590Z digest=sha256:1b6ce74e5678ed1edb5f58acb17e433569d44f36463a4dba0eb1ee071a052676

Observation b0aa3d19-33ab-472c-889b-9bc74835f582 · outbound

This paper cites White-box Membership Inference Attacks against Diffusion Models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation White-box Membership Inference Attacks against Diffusion Models

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.101974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.101974Z digest=sha256:bfe7ff49c855ffb482036d73b98113ec1e7f23f83463e2446347186797f6ae4a

Observation 7611d84e-c644-41fc-a50f-ab0eeb7fee5b · outbound

This paper cites Scalable Private Learning with PATE.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Scalable Private Learning with PATE

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.105614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.105614Z digest=sha256:4174784ab8c63a8e13ccd3ec2e2acbaa8998ef21695f94f2d6269582c0701d81

Observation a3bd8337-36f6-4b9d-b526-b00c6dc2aaf9 · outbound

This paper cites Sinkhorn autoencoders.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Sinkhorn autoencoders

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.109853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.109853Z digest=sha256:5361dc4e2cae62ebedeb4da260f801f69b3b1a5b98a38587e165942c00cae4e9

Observation 8c7697e6-0244-4414-8ca5-6fbb06ea59dd · outbound

This paper cites Synthcity: facilitating innovative use cases of synthetic data in different data modalities.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Synthcity: facilitating innovative use cases of synthetic data in different data modalities

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.113859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.113859Z digest=sha256:0b1a4d09e3760e735f159d49fda1321383879fd068007aba21a4fa19bd680890

Observation fa5fb96c-edcc-4793-b534-629998228795 · outbound

This paper cites Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.118096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.118096Z digest=sha256:4014bb9faf8935764bcd92c1ff45bfda600f8a6bb9c46ddaa33669b0f82f9ef5

Observation ae4fcf72-18ac-4e8d-8c8a-9d147e42b3af · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.121817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.121817Z digest=sha256:b3ff35877877b8b8fdc65702b69f34d9f62d2a26764da72ebe2e98a4173e32b6

Observation 1373eecc-ced8-49d3-99eb-269eea47a611 · outbound

This paper cites Generating diverse high-fidelity images with vq-vae-2.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Generating diverse high-fidelity images with vq-vae-2

Reference 92

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.125208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.125208Z digest=sha256:b4650779ad2fd49f78a3ebbef449e0b6c1f26065caf2d462debb147c4081064d

Observation beace0a0-8e3a-4e10-b789-f74732d2c372 · outbound

This paper cites High-resolution im- age synthesis with latent diffusion models.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation High-resolution im- age synthesis with latent diffusion models

Reference 93

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.129237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.129237Z digest=sha256:6d26c207e1b497308a6912cd0460fcb0ba44f920f9bfc5a83a631bb5df3b481a

Observation 49567043-a131-49ee-9886-77115d25949c · outbound

This paper cites Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 94

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.132518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.132518Z digest=sha256:4a18a2ae1aaf6ef16470b56576ebdd8bfa7e681164dc1c4c15baa8bc7cef8f26

Observation 97972cef-adae-4d1b-94fd-c0fd9090ebc3 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479– 36494, 2022.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479– 36494, 2022

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:12:18.111428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:17.136757Z digest=sha256:06b7a1a32c4ec6aced21d7448aa7319f40427fbb9339ce4c36b3559f7ae8e87f

Observation 6024980a-1fac-4b5b-8ea9-c6e3b63e3dd7 · outbound

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

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.140839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.140839Z digest=sha256:82c58560e8958c328848be18dae179a8c3828908d78fe8301890fb9de7eba4df

Observation 1509a925-dc97-45dc-887a-21f2c0e0f884 · outbound

This paper cites Improving GANs Using Optimal Transport.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Improving GANs Using Optimal Transport

Reference 97

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.145012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.145012Z digest=sha256:ad74fcdf039ce0d92e01a0bea30cbbfbfde73c419b8e3bdb5e44fa54f44054c7

Observation 5c890f26-eb7e-46a0-9187-3a81824672dc · outbound

This paper cites Synthetic Data: Revisiting the Privacy-Utility Trade-off.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Synthetic Data: Revisiting the Privacy-Utility Trade-off

Reference 98

Resolution
unresolved
no resolver link, observed 2026-08-06T23:12:17.148866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:12:17.148866Z digest=sha256:358c5dd449a77360a1e339791e4d65962fe0e5f7d95167a667e9cae186500c5e

Observation 1151e7fe-cd7e-40fa-a798-73df179fa20b · outbound

This paper cites Dragdiffusion: Harnessing diffusion models for interactive point-based image editing.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Dragdiffusion: Harnessing diffusion models for interactive point-based image editing

Reference 99

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:12:18.099537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:17.153454Z digest=sha256:41a03a9c6a35dd8549f6703dd8f9d9107df28ad30ba701be4a026b328582573f

Observation ff23c053-8f0a-4d76-86e1-89e55f7fb45a · outbound

This paper cites Diversity is definitely needed: Improving model-agnostic zero-shot classi- fication via stable diffusion.

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation Diversity is definitely needed: Improving model-agnostic zero-shot classi- fication via stable diffusion

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:12:18.089854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T23:12:17.157633Z digest=sha256:63b03601bc0c812d8a4cead9a4a491c9d24a13a56c59a41526b47dacb62ca365

Pith citing papers

Observation 59146985-9284-4472-8135-14385c2f8b57 · inbound

CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis cites this paper.

CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-05-14T21:18:00.146228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-14T21:10:36.000486Z digest=sha256:8457b080a23bfbca8cba49730480b4051e5195e682be0f0459983a1d721b9426