Paper Citation Record · LEDGER

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

As of 6 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2604.21041.

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

pith.paper-citation-record.v1
2604.21041 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T00:01:14.282766Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

26 of 26 outbound references displayed

verified exact1
verified fuzzy24
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4204e3dc-3e3f-491b-8173-ff52f3260e06 · outbound

This paper cites Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.287420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9aea3190-0231-4392-9f77-e2a6957ef642 · outbound

This paper cites Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.280053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0d2d5615-35b4-4a93-bece-2296f5206f77 · outbound

This paper cites FLARE up your data: Diffusion-based Augmentation Method in Astronomical Imaging.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks FLARE up your data: Diffusion-based Augmentation Method in Astronomical Imaging

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:51:02.937852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 06754878-4764-481a-b479-bfd937f90e49 · outbound

This paper cites The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.268816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 26d2df13-5f55-4e58-b40f-40421c1b43f8 · outbound

This paper cites Introducing SDICE: An Index for Assessing Diversity of Synthetic Medical Datasets.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Introducing SDICE: An Index for Assessing Diversity of Synthetic Medical Datasets

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.257925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1ff71858-c4f9-41c4-b6ab-de5fdc859a83 · outbound

This paper cites LAION-5B: An Open Large-Scale Dataset for Training Next Generation Image-Text Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks LAION-5B: An Open Large-Scale Dataset for Training Next Generation Image-Text Models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.254269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14bba708-8300-4bcd-a586-fdd7eaea6bbc · outbound

This paper cites General Data Protection Regulation (GDPR).

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks General Data Protection Regulation (GDPR)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.250501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ddbc833a-fa00-4c4b-a673-220fc867792e · outbound

This paper cites The European Union General Data Protection Regulation: What It Is and What It Means.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks The European Union General Data Protection Regulation: What It Is and What It Means

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.265338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e463ad49-fcb1-47c3-8907-4fc7dbd6ad71 · outbound

This paper cites A Guide to the California Consumer Privacy Act of 2018.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks A Guide to the California Consumer Privacy Act of 2018

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.272706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6a5a7bf-1218-49f7-ba22-f39fc53877f5 · outbound

This paper cites Towards Making Systems Forget with Machine Unlearning.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Towards Making Systems Forget with Machine Unlearning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.291283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9033684a-ea1d-4997-9089-b91121dd1722 · outbound

This paper cites Making AI Forget You: Data Deletion in Machine Learning.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Making AI Forget You: Data Deletion in Machine Learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.239836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3b387bc2-4ee5-4875-b447-0434f0891990 · outbound

This paper cites Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.243199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 307a12bd-bf81-4a06-8c05-07eb4189f489 · outbound

This paper cites SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-14T02:20:20.283959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 93573add-9ad9-493e-9957-32c2e5e3abd6 · outbound

This paper cites Eras- ing Concepts from Diffusion Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Eras- ing Concepts from Diffusion Models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.226514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 76933bc7-cc3b-4ba2-9eb4-f87c62b1706a · outbound

This paper cites Unified Concept Editing in Diffusion Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Unified Concept Editing in Diffusion Models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.246657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2662fe34-5e90-4e3d-80bb-1b8478305080 · outbound

This paper cites Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.261587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c6264f7d-3474-4993-a1a8-e73333298e1e · outbound

This paper cites MACE: Mass Concept Erasure in Diffusion Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks MACE: Mass Concept Erasure in Diffusion Models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.219271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 77c472cd-6ced-4346-9424-35cf758250d1 · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-Based Weight Saliency in Both Image Classification and Generation.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks SalUn: Empowering Machine Unlearning via Gradient-Based Weight Saliency in Both Image Classification and Generation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.229616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2b0caa7a-8927-46c8-bb9a-98a020a30e2f · outbound

This paper cites Fine-Tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Fine-Tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.215638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bc8f873f-e1de-41c8-95f7-215e16de1596 · outbound

This paper cites Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.208604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 748aaf25-062c-4183-9f41-cfccc5421374 · outbound

This paper cites Boosting Alignment for Post-Unlearning Text-to-Image Generative Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.276249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 062350ed-cd23-4e19-99ab-9d36c27893ca · outbound

This paper cites Denoising Diffusion Probabilistic Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Denoising Diffusion Probabilistic Models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.212257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 84e32961-bcca-4ae4-adde-ce49136f81a4 · outbound

This paper cites High-Resolution Image Synthesis with Latent Diffusion Models.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks High-Resolution Image Synthesis with Latent Diffusion Models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.223016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9784dad1-5ae7-4964-822f-eedfb603c61c · outbound

This paper cites One-Dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks One-Dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.236530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 324ad130-a2cb-48f0-a229-9187e0f10741 · outbound

This paper cites Under- standing Deep Learning Requires Rethinking Generalization.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Under- standing Deep Learning Requires Rethinking Generalization

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.232771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c69c2e40-5653-479e-a907-5b2fdd74620c · outbound

This paper cites Image Style Transfer Using Convolutional Neural Networks.

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks Image Style Transfer Using Convolutional Neural Networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:57:56.283686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.