Pith. sign in

Paper Citation Record · LEDGER

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

As of 9 August 2026, this Paper Citation Record lists 100 of 104 outbound references and 0 inbound Pith citation observations for arXiv:2607.13541.

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

pith.paper-citation-record.v1
2607.13541 v1

Coverage vector

measured 100 of 104 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T04:57:37.796578Z

measured 100 of 100 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

100 of 104 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved99
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 99d373a0-027a-4394-ae6a-175c35fd8fe5 · outbound

This paper cites Fake it till you make it: Learning transferable representa- tions from synthetic imagenet clones.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Fake it till you make it: Learning transferable representa- tions from synthetic imagenet clones

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.010027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.010027Z digest=sha256:c47ad3286b085bffa39654d64971d45cecd8514cb692e901cf722932d6a56638

Observation 3a93f91c-71da-4125-8c3d-22af5036b321 · outbound

This paper cites Deep residual learning for image recognition.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Deep residual learning for image recognition

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.065780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.065780Z digest=sha256:11e60fd725472ebf449b9c2930bc05f6fd0b6bf8bad3baf283dbffa2382542e7

Observation 4e8adba3-d40f-4536-b1f4-68f50d2b41f2 · outbound

This paper cites What chatgpt and generative ai mean for science.Nature, 614(7947):214–216, 2023.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training What chatgpt and generative ai mean for science.Nature, 614(7947):214–216, 2023

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.146147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.146147Z digest=sha256:82dc35e73654ef8581de59a42546bb98554167a82915b1c693a853ffbb992824

Observation 9b6702e7-b65e-4d97-827a-7ebbce26062b · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.228610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.228610Z digest=sha256:27f3680ed047b7f560e99a2216d69d0df7cfd8a98c8ad6fb331c52122e679baf

Observation 11ec654e-58a8-4f1a-96b2-6c17c071f9bd · outbound

This paper cites Real- fake: Effective training data synthesis through distribution matching.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Real- fake: Effective training data synthesis through distribution matching

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.311903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.311903Z digest=sha256:dcf9acba4b70f6f9f4db00db55ea6da2fc1705d628561bcedc47f013b9a77260

Observation 262148d1-7a21-49cb-b637-3f38cbe693b5 · outbound

This paper cites Is synthetic data all we need? benchmarking the robustness of models trained with synthetic images.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Is synthetic data all we need? benchmarking the robustness of models trained with synthetic images

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.411638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.411638Z digest=sha256:e90be1166c7f95fa7a2f3c32e3381273fc7911810ffd7693e68901f761c50240

Observation 220ebb28-21ff-4f4b-a27f-1f66560f5e94 · outbound

This paper cites Scaling laws of synthetic images for model training.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Scaling laws of synthetic images for model training

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.478207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.478207Z digest=sha256:755e16491e00676e6849dece43495754ef942c2b1509e116a0530d2ed6ba88b4

Observation bc782a61-4145-443d-9eeb-aa5dba19a8fe · outbound

This paper cites High-resolution image synthesis with latent diffu- sion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training High-resolution image synthesis with latent diffu- sion models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.530554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.530554Z digest=sha256:de6c6ab6abc483de1015f7aaaf2ec37e1bd03c5c8294b6f7a71b75bd022696ca

Observation 62da9937-8304-4edc-ae01-c1c68a9a23e5 · outbound

This paper cites Flux.1 kontext: Flow matching for in-context image generation and editing in latent space, 2025.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Flux.1 kontext: Flow matching for in-context image generation and editing in latent space, 2025

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.586443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.586443Z digest=sha256:f7f9817d174d91adbdb89b538025f91afcd475321b39ec0853cea2ba13aafb6c

Observation 9cf28029-ba88-4672-a388-f9480596cb26 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.694774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.694774Z digest=sha256:7432222cec8b4a53f9dee104b47cae62b5148ba204aab448481203d64252ae26

Observation 8652b818-8eff-4210-bc1c-b0721af0a717 · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.773566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.773566Z digest=sha256:7a7346931b67e967784d83347c63f59fd10e47147cedd1cc15bd0c97a46d2248

Observation afc40952-4dfd-4f35-ae5e-1dcbe41a00f4 · outbound

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

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.853983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.853983Z digest=sha256:426635777cb703858c25cb3b20ab66daade731dca53350812c3b952587564c77

Observation bbb9bcc4-9b7b-4ea1-91b2-65c710a73a34 · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Cosmos World Foundation Model Platform for Physical AI

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:30.959222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:30.959222Z digest=sha256:cca4fa21343f86aeb4a5917d13370b0ee2416398e3884f093222c3e193d8e186

Observation 858d766d-dea2-4c80-a352-1953e1965e89 · outbound

This paper cites Does training with synthetic data truly protect privacy? InThe Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Does training with synthetic data truly protect privacy? InThe Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.063341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.063341Z digest=sha256:a6aecce1bf68c3ec7432cc130537b4df7b19e1ff8cab07f06ce121faefa9281a

Observation 1c327ff9-c6e4-4461-8fc7-2c431062660c · outbound

This paper cites Membership inference attacks against machine learning models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks against machine learning models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.139090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.139090Z digest=sha256:97834d8766ce14f8d09a5ca5d253f9a2aec1e40f9dd37fd0d607f16d3a2fc761

Observation 166e684c-9581-4b88-9b72-dc31431c97e1 · outbound

This paper cites Membership inference attacks from first principles.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks from first principles

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.239628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.239628Z digest=sha256:a35c349b5a11d704fb85d293ceb04e211ca5ac183d452703608f289b6c69cf4f

Observation 0d220795-0f12-4d9c-800b-ebd650b7d297 · outbound

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

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Comprehensive privacy analysis of deep learning: Passive and active white-box infer- ence attacks against centralized and federated learning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.320852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.320852Z digest=sha256:b88a1ed53248f1286fd2240d2d5b97c574b0d042864fb2c37b5c24f73e50e4b0

Observation 5e8a0dc7-25ad-4586-8d59-c278c92a07b2 · outbound

This paper cites Privacy risk in machine learning: Analyzing the connection to over- fitting.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Privacy risk in machine learning: Analyzing the connection to over- fitting

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.401867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.401867Z digest=sha256:129c8f81c33cfc2905787e937b0126981e837be93eb3c7b92d0c85dce38c9c0a

Observation f8926530-87ba-4962-9c42-024804a1c835 · outbound

This paper cites Membership inference attacks as privacy tools: Reliability, disparity and ensemble.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks as privacy tools: Reliability, disparity and ensemble

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.481626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.481626Z digest=sha256:23bb695c48ee22efa325b841febe03938adc270c6e449eb69590c4bbcc5127c1

Observation 5d87156c-1201-4f0e-92e9-445fd0237e5c · outbound

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

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Gan-leaks: A taxonomy of membership inference attacks against generative models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.562695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.562695Z digest=sha256:fb76eb240b683a18e71e32d8fd05e53eacb5a58fe3aab88b0f65c6d751f7ad10

Observation 610587c9-66f2-44ab-8ed2-6b52dd37e613 · outbound

This paper cites Enhanced label-only membership inference attacks with fewer queries.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Enhanced label-only membership inference attacks with fewer queries

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.647702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.647702Z digest=sha256:da71df5931f0cb62ca6e023ea476e1adac48a64443f41ad2315395732e640d5e

Observation f0839358-9972-40fc-98ce-154af4090878 · outbound

This paper cites A method to facilitate member- ship inference attacks in deep learning models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training A method to facilitate member- ship inference attacks in deep learning models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.768887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.768887Z digest=sha256:16443d68a0a869a7852607f9ce074badec96334e1aa0cbad7f64ab97f4fe1f7d

Observation 649b0bcd-543f-4ed1-93dc-e72723c7e447 · outbound

This paper cites Reconciling privacy and accuracy in ai for medical imaging.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Reconciling privacy and accuracy in ai for medical imaging

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.774882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.774882Z digest=sha256:0dfe9ae89dab89d52d0044a170666f7edfb286f0bb888b6fdba89d3d3c09b574

Observation 77de4dff-afc3-4c11-8b93-ab67b959ad66 · outbound

This paper cites Watermarking makes language models radioactive.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Watermarking makes language models radioactive

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:31.909044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:31.909044Z digest=sha256:d7ce3db860e226c403e275a23aca07e3184867d71080099f46017877a1689ff2

Observation ff76adc2-1d75-47a0-94f8-50f994c5b034 · outbound

This paper cites Any-resolution ai-generated image detection by spectral learning.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Any-resolution ai-generated image detection by spectral learning

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.059247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.059247Z digest=sha256:ecd6fb524bc31699325175f0588954a2359b0f19fd42898ca05c90bced018bbd

Observation 54d721ca-2de7-4293-bfc7-45f426d05219 · outbound

This paper cites Towards universal fake image detectors that generalize across generative models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Towards universal fake image detectors that generalize across generative models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.189336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.189336Z digest=sha256:c6ba477d5bf386d62a9d2ebb9a69c747c8c331e7205e0ff4a91768dfe232b2d1

Observation 230631d5-c14e-456f-bb87-b68e37273d3b · outbound

This paper cites Membership inference attacks and de- fenses in neural network pruning.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks and de- fenses in neural network pruning

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.289001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.289001Z digest=sha256:b1db456733d57ed1933a2b6ca291de03b6befcefeccc650a14c396b25cbb2388

Observation 5dc662ac-3c89-4fd2-8f71-7d4fb6310091 · outbound

This paper cites Privacy risks of securing machine learning models against adversarial examples.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Privacy risks of securing machine learning models against adversarial examples

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.407787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.407787Z digest=sha256:7f06c70e2695be97b7c13e448659e8014a1ebbd947e4863d105fa3c9dd9e9c14

Observation d93252a0-f08e-4040-bb58-0ea447c33957 · outbound

This paper cites Low-cost high-power membership inference attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Low-cost high-power membership inference attacks

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.525356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.525356Z digest=sha256:c333e78aaaf8364819f11086df1c22bdd03d1e2d5c8c2c49da6910d106af4e42

Observation 76840450-add2-4acd-9ca0-018c520b5cf7 · outbound

This paper cites SDXL: Improving latent diffusion models for high-resolution image synthesis.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training SDXL: Improving latent diffusion models for high-resolution image synthesis

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.681563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.681563Z digest=sha256:9610f20d0a859e4df1a28fa20fb889c9b2155040656937427bcbd1571374e40b

Observation eb138729-f786-41d7-9fc4-44cceb58027c · outbound

This paper cites Scalable diffusion models with transformers.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Scalable diffusion models with transformers

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.843838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.843838Z digest=sha256:c0b9e7561ee27e780561b13ec917ea0ebfb1e2517e91f0a60aa776ee9b669620

Observation 9daf66e1-278c-49e1-beb1-3241e026d38b · outbound

This paper cites SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.950850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.950850Z digest=sha256:392a5f704d9f92f628f9d22dfdf8b7317dede642df05ef6348b54757bb807d6d

Observation 8af0fc2b-c3a5-47f8-8796-41953c19c7ad · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training LoRA: Low-rank adaptation of large language models

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:32.953669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.953669Z digest=sha256:735cc8feb2690958397422ad57fa981f246cbbde0f2ab0710a377d03a0668594

Observation 79938c94-2d4b-43cb-9ebd-102ea9c61730 · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 34

Resolution
parse uncertain
no resolver link, observed 2026-08-02T04:57:32.959011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:32.959011Z digest=sha256:af325726dcc34161ca1145b27718a8a2c93dfc619655c70490ee4bf39ea96b72

Observation 538c64ae-6e50-4f34-aae3-ee090169943f · outbound

This paper cites Lens: Localization enhanced by nerf synthesis.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Lens: Localization enhanced by nerf synthesis

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.020369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.020369Z digest=sha256:3c80cf46774bce88e098610f5dcc13cb447c6fabb2f93f04bd9dba23fc070e85

Observation dfb250b2-97da-4996-8d36-eba295542adf · outbound

This paper cites Nerf-supervision: Learning dense object descriptors from neural radiance fields.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Nerf-supervision: Learning dense object descriptors from neural radiance fields

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.102854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.102854Z digest=sha256:143458b0dce906d2ee3d73f74f9f4f8d3fb927773396995916b38ee708b2ba9a

Observation 75244365-84fd-477e-93f3-64442891dd90 · outbound

This paper cites Augmented reality meets computer vision: Efficient data generation for urban driving scenes.International Journal of Computer Vision, 126(9):961–972, 2018.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Augmented reality meets computer vision: Efficient data generation for urban driving scenes.International Journal of Computer Vision, 126(9):961–972, 2018

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.174179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.174179Z digest=sha256:9c899e6ee42f1e7a2dafc42160d31e090a601ee93028967e4eed376dd93de80f

Observation 8d12a0cf-4383-4c28-a679-9b57f8f0f730 · outbound

This paper cites Learning deep object detectors from 3d models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Learning deep object detectors from 3d models

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.235807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.235807Z digest=sha256:3569f71de846024c15ad8be9e6eaf0838e5eac81fa17a63149c886cab3d7830a

Observation 68a086b0-8104-4310-83f5-9a33a912fc6f · outbound

This paper cites Dataset Distillation.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Dataset Distillation

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.262320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.262320Z digest=sha256:28fba9ccc83a934238a2bacca98339e28babd68163526d26cd022e6a8b630a66

Observation 5243d175-9062-4143-b9c6-a2500afb055d · outbound

This paper cites Dataset condensa- tion with gradient matching.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Dataset condensa- tion with gradient matching

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.320424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.320424Z digest=sha256:337e53f23095b4b8d517a9fae74b06e35f0958f6e68e8315c1fbcfd8411cc024

Observation f05a058c-8d81-457c-9da3-ddd6fae43d9c · outbound

This paper cites Dataset distillation by matching training trajectories.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Dataset distillation by matching training trajectories

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.417231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.417231Z digest=sha256:eeb3e2f7cde4c1c1f9fff9fa1095401e7c10b12e6258e4b6342e9f464be1f97a

Observation 2cc151a1-ab95-4f76-b567-81163437d0ae · outbound

This paper cites Privacy for free: How does dataset condensation help privacy? InInternational Conference on Machine Learning, pages 5378–5396.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Privacy for free: How does dataset condensation help privacy? InInternational Conference on Machine Learning, pages 5378–5396

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.563912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.563912Z digest=sha256:1c4e77b7ed0e0b9b3ad2bf4026df2a0c0db6f64ccab50ccd5a4e60b3402990c3

Observation a04fc794-f577-4115-b29f-660610762687 · outbound

This paper cites No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy".

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy"

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.724324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.724324Z digest=sha256:4cadccfe8b69f3068b99225eaf101eaa89cbaf3bd85c3cdfbc8f9d1e7cd19b46

Observation ce9eb20e-0375-41e7-9cdd-9faf0bee123f · outbound

This paper cites Backdoor attacks against dataset distillation.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Backdoor attacks against dataset distillation

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.758520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.758520Z digest=sha256:5c17a981f52e4b69476e417c32146c2217f35ffcd9b63cce8670d34d4d857fa0

Observation d67e36e2-6919-4370-8eab-56c9508af2f7 · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.833609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.833609Z digest=sha256:f3356245966c676916eb90dfcfa57830b593ef3193154ae66c3a240c38a06531

Observation 21c26ff2-6014-46f5-aa8f-7a6bb073d409 · outbound

This paper cites GR00T N1: An Open Foundation Model for Generalist Humanoid Robots.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:33.913780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:33.913780Z digest=sha256:7e749cd12747a31294735dc290a348b3ef2e19415ab4edae2df33a22dd498c89

Observation 1df9673d-890a-4928-9f9f-01637cd79a34 · outbound

This paper cites Membership inference attacks and defenses in classification models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks and defenses in classification models

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.020785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.020785Z digest=sha256:42a109ff92a99c556a59ce9ba6af0fae10217e85245d8cd6bc243d821cb2fa50

Observation 4c0e020f-c0cf-4e54-bb2e-ad9c21737690 · outbound

This paper cites Rigging the foundation: Manipulating pre-training for advanced membership inference attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Rigging the foundation: Manipulating pre-training for advanced membership inference attacks

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.115568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.115568Z digest=sha256:ea4ddd743169f83bc81606ff91c5cb6550fda18ec5305c0f0c66618fa1de65c9

Observation 0d585179-20af-4a41-a30b-d6470e95486b · outbound

This paper cites Enhanced membership inference attacks against machine learning models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Enhanced membership inference attacks against machine learning models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.158699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.158699Z digest=sha256:8063e8a0e1b392c4db21b2826d6040b5e2162c92c33830c84b0ddaac042faf3d

Observation b511950a-b20e-4bee-97c2-8497c72e9708 · outbound

This paper cites Armanuzzaman, and Ziming Zhao.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Armanuzzaman, and Ziming Zhao

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.206621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.206621Z digest=sha256:d6d5858b59f0a3c29907f67dede6fd6b12a98b350c216e4ae80a79e78446affd

Observation 8a96f31b-19d4-4ea9-903a-c80d24f43e54 · outbound

This paper cites Practical blind membership inference attack via differential comparisons.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Practical blind membership inference attack via differential comparisons

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.250739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.250739Z digest=sha256:3e8ba472f914d18a2c475c07a04847ce57ce56ae890b62fe1799b874447d8ffd

Observation 55577ac1-b42b-4e40-a844-7397408c1008 · outbound

This paper cites SOFT: selective data obfuscation for protecting LLM fine-tuning against membership inference attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training SOFT: selective data obfuscation for protecting LLM fine-tuning against membership inference attacks

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.334354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.334354Z digest=sha256:db142f968c3b2aeaf80e7dacf5be93f64f52ed3a66fe2289fda4c7b4910cfe5f

Observation 28a919c1-2c6c-4c03-bacc-cfd32820dca1 · outbound

This paper cites Querycheetah: Fast automated discovery of attribute inference attacks against query-based systems.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Querycheetah: Fast automated discovery of attribute inference attacks against query-based systems

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.395565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.395565Z digest=sha256:106f93db13b5b77547043eb10d4cbf494426184f3a1e781be622f33190a2d3f5

Observation c0bd0adc-9240-4db8-b69b-cf1b9b996b59 · outbound

This paper cites SLMIA-SR: speaker-level membership inference attacks against speaker recognition systems.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training SLMIA-SR: speaker-level membership inference attacks against speaker recognition systems

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.467672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.467672Z digest=sha256:d4ec523836d5fa522e0dde2caf0ef67a31bdd81ebad648194b71fffb9f617d55

Observation 8aaf7bc9-a0a5-48c7-b050-646d4bf3af59 · outbound

This paper cites Imitative membership inference attack.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Imitative membership inference attack

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.535189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.535189Z digest=sha256:f3ae15c955fe6d0ba56ca95892de2e9d5264a692c02d1e650e40c9b5ce80e26b

Observation e11fd00b-ec98-4680-a754-ad36142a21a9 · outbound

This paper cites Cascading and proxy membership inference attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Cascading and proxy membership inference attacks

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.625312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.625312Z digest=sha256:d91dd2354aa05e38dca5aef8a439b6690140211514dd385ef73773f93b383ae1

Observation 14e416e0-c0b1-48a9-a42c-5b7efe11b7ab · outbound

This paper cites Please tell me more: Privacy impact of explainability through the lens of membership inference attack.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Please tell me more: Privacy impact of explainability through the lens of membership inference attack

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.710953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.710953Z digest=sha256:d14cf5c11eb424e550d59078fe393037b90cde675261d6e7704d0bedd0d5ff4f

Observation f16d490c-1a16-49ac-a353-45c443c8a1b4 · outbound

This paper cites A unified membership inference method for visual self-supervised encoder via part-aware capability.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training A unified membership inference method for visual self-supervised encoder via part-aware capability

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.798852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.798852Z digest=sha256:aa2166c621692ed452276e16af9621ed8599128da4dc0005fdaefe1247b570c2

Observation 82b32d39-870b-462d-be19-5818973f4f64 · outbound

This paper cites Encodermi: Membership inference against pre-trained encoders in con- trastive learning.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Encodermi: Membership inference against pre-trained encoders in con- trastive learning

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.885064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.885064Z digest=sha256:c780e2ee0ceaa4bed1f4025a7b5dd90f74c15051c3998cb5c4c6e9bd703b168b

Observation d84813e8-534f-4c6f-b1fb-2073a422cc45 · outbound

This paper cites When machine unlearning jeopardizes privacy.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training When machine unlearning jeopardizes privacy

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:34.973849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:34.973849Z digest=sha256:835e2f768c5205dc8541d058abdddb9cbd2e4b75648885b0e1516b051e17af2b

Observation 41fd2fc9-f98d-42bd-ad99-58e1ecb2ad3c · outbound

This paper cites Compleak: Deep learning model compression exacerbates privacy leakage.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Compleak: Deep learning model compression exacerbates privacy leakage

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.060536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.060536Z digest=sha256:880b1505f70fcb06ebec89f2d86a2830520e9708e6a49b17ce07b7b04993099c

Observation 46c1e18b-d8d0-4fcd-85d3-a3caa1b238ba · outbound

This paper cites Riddle me this! stealthy membership inference for retrieval-augmented generation.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Riddle me this! stealthy membership inference for retrieval-augmented generation

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.144991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.144991Z digest=sha256:fc9b7d9f3843b85df00bde912972d79e1b1156186a7d453ab7271f387c5334d4

Observation 2eace009-6602-4129-a067-8c94a5392d86 · outbound

This paper cites InProceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, CCS 2025, Taipei, Taiwan, October 13-17, 2025, pages 4184–4198.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training InProceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, CCS 2025, Taipei, Taiwan, October 13-17, 2025, pages 4184–4198

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.222447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.222447Z digest=sha256:02081c78a816b0ee25c8f1779e31e0fdd710615095a0e093fbb5a5c782a54299

Observation 10870001-1ebc-48ab-9602-e1fde4a940b7 · outbound

This paper cites Membership inference attacks against vision-language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks against vision-language models

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.293049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.293049Z digest=sha256:c2ca1e37fd37ba9f54bd83878d9297338cef03999f3f6881d5c451516028a3a5

Observation 5bab84ce-04cf-4b5c-a690-c62b59c47b98 · outbound

This paper cites Did the neurons read your book? document-level membership inference for large language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Did the neurons read your book? document-level membership inference for large language models

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.377700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.377700Z digest=sha256:0ae09fc3bcdf536f5055f3c4af31e959f758d5248e7bdbc860f4616bb5486d2e

Observation a656117e-0f3e-4875-9229-c803cd043a1d · outbound

This paper cites Membership inference attacks against in-context learning.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks against in-context learning

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.439176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.439176Z digest=sha256:0e71cfa0f99fa9ded7e5970ecba21b22832bd5b4fabe31fac7f6875bb80fb5f6

Observation 36ce452c-8f1d-4c82-a412-d2d32c139464 · outbound

This paper cites Towards label-only membership inference attack against pre-trained large language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Towards label-only membership inference attack against pre-trained large language models

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.501004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.501004Z digest=sha256:09ddcf731cd12b4d2d63b28ca01aef405075ff609b4067062a04e6a96c8bfadf

Observation 06f4d320-72f1-4bcf-b5b9-22d347ae70fa · outbound

This paper cites Membership inference attacks on tokenizers of large language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Membership inference attacks on tokenizers of large language models

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.560562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.560562Z digest=sha256:73580f61fbde7a11a836ff14136903ff2c277af3540b76927661e1867313331b

Observation 7fa14882-134a-4f8f-a7ec-c0b3ac5361a8 · outbound

This paper cites Window-based membership inference attacks against fine-tuned large language models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Window-based membership inference attacks against fine-tuned large language models

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.595794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.595794Z digest=sha256:7a40ab142e562c2fa9b15c037caf51ee6df00680d1a5236d65997d41c73991be

Observation 2befd7dc-9990-4da1-9b81-4deb60e52c12 · outbound

This paper cites Vidleaks: Membership inference attacks against text-to-video models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Vidleaks: Membership inference attacks against text-to-video models

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.660057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.660057Z digest=sha256:ef936b4a0be6813a58d41ba71fe390905a818f4357b6ef8c1dd1425f8c9b7979

Observation c8010beb-2dbf-4773-bcf0-967ded80fddb · outbound

This paper cites Diffence: Fencing membership privacy with diffusion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Diffence: Fencing membership privacy with diffusion models

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.729855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.729855Z digest=sha256:ec66b6f0494468dd7220cc79ccccc4965aec57f113a6983e124e341db7a94de9

Observation a0575827-1f8f-40b2-937a-9d5d308a7813 · outbound

This paper cites Black-box membership inference attacks against fine-tuned diffusion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Black-box membership inference attacks against fine-tuned diffusion models

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.814269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.814269Z digest=sha256:bb7d37754962654b4dd919f3c8292427749083b029b2b81088f632c59e29b0c4

Observation 9deac9f4-5442-4f94-93b1-e0f1ee488827 · outbound

This paper cites Inference attacks against graph generative diffusion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Inference attacks against graph generative diffusion models

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.897021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.897021Z digest=sha256:bc1e17089922a95955db32f1d46e69b81ecf9e141395903da24ff22c8abb9c3a

Observation cb58fb81-368e-4936-88c4-da41464fdac8 · outbound

This paper cites Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:35.964714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:35.964714Z digest=sha256:13236fc8ef050bf5fb56f83a43ff3401687d066518cc1bff98d6bb5818bef78b

Observation c1ea287c-e76e-43ba-bdcb-8112890afc30 · outbound

This paper cites Does learning require memorization? a short tale about a long tail.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Does learning require memorization? a short tale about a long tail

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.039818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.039818Z digest=sha256:f066e72f1daf8d015ee36a673d4325d5610e14637da346a40b0be5c210e95499

Observation 12927411-a085-4ff5-a654-a76567d0ef36 · outbound

This paper cites What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Systems, 33:2881–2891, 2020.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Systems, 33:2881–2891, 2020

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.108192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.108192Z digest=sha256:a2b1ecb5370fe1f91c6a3f7a84ba5e1f47bf53ebdb7d8bcc6c3b2a17ab401e52

Observation e23e7b1e-9e4c-461c-bce8-6a28e99b8f80 · outbound

This paper cites A closer look at memorization in deep networks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training A closer look at memorization in deep networks

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.198843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.198843Z digest=sha256:5904038f94002b45c19962654cc3ccd5bcd66da6af24363414a472b8901d52f0

Observation 48c1ea80-cece-4b92-ab18-e02a9cbac311 · outbound

This paper cites Memorization through the lens of curvature of loss function around samples.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Memorization through the lens of curvature of loss function around samples

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.295812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.295812Z digest=sha256:8412e96b644cd19a068ba02dc34925e06f942134e4b2765b03841c6cffde033c

Observation 9c03f369-1746-4900-8f1f-31d7f06da97c · outbound

This paper cites Seqmia: Sequential-metric based membership inference attack.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Seqmia: Sequential-metric based membership inference attack

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.377594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.377594Z digest=sha256:0b3be22cec494ee481efc1659526130a3981dac5defe377d18c80a669992ed18

Observation aaa4ba28-8389-4288-b8d0-7270367a33a6 · outbound

This paper cites Is difficulty calibration all we need? towards more practical membership inference attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Is difficulty calibration all we need? towards more practical membership inference attacks

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.489467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.489467Z digest=sha256:fa3392496e35ad8fd5443f182aa916e60c06c54cb5715076b6874fcc33c039d9

Observation a959c678-ba50-4c0d-81ca-5cae3b5939a8 · outbound

This paper cites Mem- bership inference attacks by exploiting loss trajectory.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Mem- bership inference attacks by exploiting loss trajectory

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.587003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.587003Z digest=sha256:56c76bd4b256fac43d4f2b10f8354a31adc61e5d68233c2d78ae7b75de9e0783

Observation 0bd5402d-7df3-4a36-8e81-de6c8a46d57b · outbound

This paper cites Watch out! simple horizontal class backdoor can trivially evade de- fense.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Watch out! simple horizontal class backdoor can trivially evade de- fense

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.674933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.674933Z digest=sha256:2a648de8369c19511dac913ee98de32afe173e651c49915e604a237826f13902

Observation 4f0faab7-52fd-4372-8d85-38dcf969fed2 · outbound

This paper cites Yes,{One- Bit-Flip}matters! universal{DNN}model inference depletion with runtime code fault injection.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Yes,{One- Bit-Flip}matters! universal{DNN}model inference depletion with runtime code fault injection

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.743685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.743685Z digest=sha256:f83c80a7e3774ce9dfadf917cb49da5a5969f843de641c1369acd61b3a5688f2

Observation cf12ab68-3923-439d-9cc1-6a197fb5a601 · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.799997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.799997Z digest=sha256:b311e58e938d092319a7728dc33a16f32575e791e5ffda18fed3c3b2bfa47367

Observation df3ea377-234b-45ea-b9dc-d3cda6ad1ef1 · outbound

This paper cites Patternnet: A benchmark dataset for performance evaluation of remote sensing image retrieval.ISPRS Journal of Photogrammetry and Remote Sensing, 145:197–209, 2018.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Patternnet: A benchmark dataset for performance evaluation of remote sensing image retrieval.ISPRS Journal of Photogrammetry and Remote Sensing, 145:197–209, 2018

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.864047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.864047Z digest=sha256:fe85f195bbfaa8668a107825c8e728ed3c1c6db5e867a55f4a609c4eb77d566c

Observation ae89051e-486f-420a-a77a-ddb9a55e4596 · outbound

This paper cites Vggface2: A dataset for recognising faces across pose and age.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Vggface2: A dataset for recognising faces across pose and age

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:36.932553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:36.932553Z digest=sha256:fb0e354dea6c1daa40fa10c932ea53dac54091a31d09744ba9203493cf6f98bd

Observation 902ef83b-204b-4ace-88dd-7ad318296d66 · outbound

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

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Imagenet: A large-scale hierarchical image database

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.001714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.001714Z digest=sha256:c3731622d3467b25f61a68602f388a174810b465056c894eac0fa12b5e63505f

Observation 1f1e036b-fb4a-4bc4-bc99-ebf1e4d02370 · outbound

This paper cites Contrastive multiview coding.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Contrastive multiview coding

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.083926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.083926Z digest=sha256:6ba765e85e0e4afa7a29ca154d4d85bee7e5538c72317f6ad8978799c1e37ae6

Observation 7c3ddd47-1bb4-4035-9dbd-453d63f8abc7 · outbound

This paper cites an unresolved cited work.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Unresolved cited work

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.140517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.140517Z digest=sha256:725d68a742248cf61843b49e6fd38daece4097d48e178fe682b53aa6c21df00a

Observation a9e5edbc-e1fb-4020-8a58-dddeebb1dbb0 · outbound

This paper cites Black-box membership inference attacks against fine-tuned diffusion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Black-box membership inference attacks against fine-tuned diffusion models

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.199852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.199852Z digest=sha256:11f373f749cfe2f454e398cad326571d0d2a1fd3b34c42e5e4c2c29596ef1688

Observation 9cc54f15-b1bd-4477-b772-815f75e9849e · outbound

This paper cites Towards reliable verification of unauthorized data usage in personalized text-to-image diffusion models.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Towards reliable verification of unauthorized data usage in personalized text-to-image diffusion models

Reference 92

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.245673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.245673Z digest=sha256:bcee3bd3330ad6f0129f03162a905744f5ec857367417cba46998aab3bc61792

Observation 1c32bc56-8f31-4a91-b10b-11e8cc3d98ae · outbound

This paper cites Pretender: Universal active defense against diffusion finetuning attacks.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Pretender: Universal active defense against diffusion finetuning attacks

Reference 93

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.325687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.325687Z digest=sha256:a667e02d5ab32ddd887a64152ef4ab56896b319eaae08683887dd89da13aca94

Observation 184ead63-cf96-43eb-ade7-6c32a2c9ae52 · outbound

This paper cites Genomic privacy and limits of individual detection in a pool.Nature Genetics, 41(9):965–967, 2009.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Genomic privacy and limits of individual detection in a pool.Nature Genetics, 41(9):965–967, 2009

Reference 94

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.381304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.381304Z digest=sha256:b26b3e0aaa31d2ac72ad00584cb773050df28d4ad68cfacc9d3f1adc054853be

Observation 90474e19-59dd-4dcd-b9da-f5cd8d4e4934 · outbound

This paper cites Prototypical networks for few-shot learning.Advances in Neural Information Processing Systems, 30, 2017.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Prototypical networks for few-shot learning.Advances in Neural Information Processing Systems, 30, 2017

Reference 95

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.436071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.436071Z digest=sha256:68307f133f67db37b47b5ff9e7d352a87b076d70351b76b5eefad378d499dca5

Observation 4a644696-7cae-40e6-b537-3be9e130e6b6 · outbound

This paper cites Prevalence of neural collapse during the terminal phase of deep learning training.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Prevalence of neural collapse during the terminal phase of deep learning training

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.487084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.487084Z digest=sha256:281adacadfbf1d5084faceed23b48b2ed820012a7b341a7cc8a8886f61faccf3

Observation 93ba1e1f-583d-446a-9dfa-05cf5aa8dd12 · outbound

This paper cites Neural collapse under mse loss: Proximity to and dynamics on the central path.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Neural collapse under mse loss: Proximity to and dynamics on the central path

Reference 97

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.503675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.503675Z digest=sha256:6faa98356d8c5fc9882aad75155e08e855f7940e32cc6ee8c4a0d473deac365c

Observation d57c3f81-597d-44d0-999d-b8c316f19d36 · outbound

This paper cites Distance-based image classification: Generalizing to new classes at near-zero cost.IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11):2624–2637, 2013.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Distance-based image classification: Generalizing to new classes at near-zero cost.IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11):2624–2637, 2013

Reference 98

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.525212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.525212Z digest=sha256:c9f58e717400fb3989df0fb19db05961e59788b2d6160bfb85c8ac003f825319

Observation 55faa7c3-c3f2-42e8-b831-4a451c1f1591 · outbound

This paper cites Cambridge University Press, 2018.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Cambridge University Press, 2018

Reference 99

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.587542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.587542Z digest=sha256:3145cb815f24339aa1201fd60e28e6c75b8227c4b50a1476f1befe3f0da5fd92

Observation eeec5a0c-a397-4942-9545-ef4889d8f1d5 · outbound

This paper cites Calibrating noise to sensitivity in private data analysis.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Calibrating noise to sensitivity in private data analysis

Reference 100

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.697398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.697398Z digest=sha256:12035c0ff229bc43edf089a985f75ff847e28990426bf40a92502d9a89ddc8d9

Observation fedb3970-4ec8-4ea4-85ce-058345607283 · outbound

This paper cites Deep learning with differential privacy.

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training Deep learning with differential privacy

Reference 101

Resolution
unresolved
no resolver link, observed 2026-08-02T04:57:37.796578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:57:37.796578Z digest=sha256:a89a6e19975c1fc8574430fa6339439d1feb274383948cf134088b7d61b09d96

Pith citing papers

No inbound Pith citation observations are available.