Paper Citation Record · LEDGER

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention

As of 19 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2507.13598.

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

pith.paper-citation-record.v1
2507.13598 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:26:21.382657Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T19:58:59.208179Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact3
verified fuzzy21
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 88913467-f0c2-4c8c-a952-6542ce0b49e5 · outbound

This paper cites Data unlearning in diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Data unlearning in diffusion models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:22.034379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f8c0babb-f524-4c3c-a5a1-40f41e2fcb5d · outbound

This paper cites Nudenet: Neural nets for nudity classification, detection and selective censoring.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Nudenet: Neural nets for nudity classification, detection and selective censoring

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:22.025076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 33efca03-8337-4be4-a2a9-5a6239e9db46 · outbound

This paper cites Stable diffusion license, 2022.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Stable diffusion license, 2022

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:22.015447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 05317691-e10e-47aa-9ab4-ac1d2b8835f8 · outbound

This paper cites Model-agnostic meta-learning for fast adap- tation of deep networks.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Model-agnostic meta-learning for fast adap- tation of deep networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.268980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67a4bbb3-122d-425d-b511-fb8f7ed09646 · outbound

This paper cites An image is worth one word: Personalizing text-to-image generation using textual inversion.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention An image is worth one word: Personalizing text-to-image generation using textual inversion

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:22.000933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5a427ba7-b5c9-486c-931f-440b05684b6c · outbound

This paper cites Erasing concepts from diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Erasing concepts from diffusion models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.991646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c17f1c4-e1f4-436c-87c9-eb2f0f923fd2 · outbound

This paper cites Unified concept editing in diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Unified concept editing in diffusion models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.982378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c1351f2b-2b97-4f10-a6ff-09a77444a97b · outbound

This paper cites HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.281979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ba8ee6-18d7-4569-846c-7126499a5d05 · outbound

This paper cites Reliable and efficient concept erasure of text-to-image diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Reliable and efficient concept erasure of text-to-image diffusion models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.972555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8850efb3-a19a-475d-9418-c0bdb1845e4c · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.288384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d67f6d15-6aa8-4bd4-bf2f-96ebb7b7dd1c · outbound

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

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention LoRA: Low-rank adaptation of large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.962970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 44f3b5e8-5809-49ac-8269-603deace43f0 · outbound

This paper cites an unresolved cited work.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.295335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46c3472-77a0-4e47-b787-e1bfea7348d4 · outbound

This paper cites Ablating concepts in text-to-image diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Ablating concepts in text-to-image diffusion models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.952594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 113af546-6422-48aa-97b4-335c1ec4dc78 · outbound

This paper cites Multi- concept customization of text-to-image diffusion.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Multi- concept customization of text-to-image diffusion

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.942538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7bb310c1-d1a8-4046-8b96-563ead9d83a0 · outbound

This paper cites Towards understanding cross and self-attention in stable diffusion for text-guided image editing.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Towards understanding cross and self-attention in stable diffusion for text-guided image editing

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.933372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 98d7d340-2893-4e82-9905-965fbde5a342 · outbound

This paper cites Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.309150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c37c99c-c3d5-4098-a576-4d4eeaa68c73 · outbound

This paper cites Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:26:21.706241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ca2f7e05-fb7b-4d2c-8637-58121466e7a9 · outbound

This paper cites Marshall, Niv Cohen, Govind Mittal, and Chinmay Hegde.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Marshall, Niv Cohen, Govind Mittal, and Chinmay Hegde

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.924134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9bed6fe-d986-4d3e-9793-58993ec8014e · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.318794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9c17fd2-3427-4b33-9622-1eaeba439659 · outbound

This paper cites Zero-shot text-to-image generation.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Zero-shot text-to-image generation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.914738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 097224c5-febd-4b76-8172-0094a64d1d89 · outbound

This paper cites Red-Teaming the Stable Diffusion Safety Filter.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Red-Teaming the Stable Diffusion Safety Filter

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.324774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d45e8569-3add-41a1-9711-5d504ef19332 · outbound

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

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention High-resolution image synthesis with latent diffusion models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.328211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66227216-a9f1-413e-9e8b-861a5b939e75 · outbound

This paper cites Representation noising: A defence mechanism against harmful finetuning.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Representation noising: A defence mechanism against harmful finetuning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.900021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b797833e-0542-4a5d-bcfd-87e1c5aaca11 · outbound

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

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.334225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8808c8-85fd-4baf-9db8-2581cb018fb9 · outbound

This paper cites Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.337175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ffda5fd-c6a9-4e94-959d-b69d81ab0dca · outbound

This paper cites an unresolved cited work.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:26:21.880086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c36a680-0067-4f00-ab11-aa96aded86b5 · outbound

This paper cites To forget or not? towards practical knowledge unlearning for large language models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention To forget or not? towards practical knowledge unlearning for large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.871348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f127bd4b-43b2-445f-9388-8135ebb4d3e3 · outbound

This paper cites Aeiou: A unified defense framework against nsfw prompts in text-to-image models, 2024.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Aeiou: A unified defense framework against nsfw prompts in text-to-image models, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.347153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f048d4-1169-46c5-bc96-939042ecfd96 · outbound

This paper cites Exploring diffusion models’ corruption stage in few-shot fine-tuning and mitigating with bayesian neural networks, 2024.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Exploring diffusion models’ corruption stage in few-shot fine-tuning and mitigating with bayesian neural networks, 2024

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-06T16:26:21.589728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 049d48c5-78aa-4424-9bf0-4a198d402a61 · outbound

This paper cites an unresolved cited work.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.353309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbf3ccb1-8b62-438c-819c-93c5cf1643f8 · outbound

This paper cites an unresolved cited work.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.356970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d93a45-ae19-478e-a6cb-f8e5bc0eaee7 · outbound

This paper cites Sneakyprompt: Jailbreaking text-to-image generative models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Sneakyprompt: Jailbreaking text-to-image generative models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.359973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516e1675-734c-425d-babc-cdf1521cb473 · outbound

This paper cites SAFREE: Training- free and adaptive guard for safe text-to-image and video generation.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention SAFREE: Training- free and adaptive guard for safe text-to-image and video generation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.862065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1022521a-65ec-4f8f-bf49-f39616a2b8e8 · outbound

This paper cites Forget-me- not: Learning to forget in text-to-image diffusion models.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Forget-me- not: Learning to forget in text-to-image diffusion models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.852073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eb8bff36-041b-4b95-b570-d7a1748584a9 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention The unreasonable effectiveness of deep features as a perceptual metric

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.842355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bb9e632d-5e40-4d4c-85b0-7c4b69a4e80e · outbound

This paper cites To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.832267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d369205e-b047-4e18-9f4d-9c0a516fc281 · outbound

This paper cites Imma: Immunizing text-to-image models against malicious adaptation.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Imma: Immunizing text-to-image models against malicious adaptation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.822594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1cffc722-56cf-49fe-8e89-0e623c93c431 · outbound

This paper cites On the Limitations and Prospects of Machine Unlearning for Generative AI.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention On the Limitations and Prospects of Machine Unlearning for Generative AI

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:26:21.429208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d24ff5ff-425b-4b6d-a9e0-0052eb3dcb93 · outbound

This paper cites Nsfw-t2i.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Nsfw-t2i

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:26:21.813031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 0ace67d7-1f63-4204-a737-e50ce86396ca · inbound

Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns cites this paper.

Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T19:58:59.208179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.