Paper Citation Record · LEDGER

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

As of 9 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2508.01272.

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

pith.paper-citation-record.v1
2508.01272 v2

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:48:34.147423Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:32:12.060869Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T22:32:12.963581Z

Reference resolution

50 of 50 outbound references displayed

verified exact2
verified fuzzy38
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb069259-c7e2-4dbf-a077-4ea5068bd6ce · outbound

This paper cites GPT-4 Technical Report.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:29.744486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38486688-1ed3-41a7-90b6-eb4ce7091895 · outbound

This paper cites Distorting embedding space for safety: A defense mechanism for adversarially robust dif- fusion models, 2025.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Distorting embedding space for safety: A defense mechanism for adversarially robust dif- fusion models, 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:41.317009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 67da2993-3a0d-4a4c-916b-3c96b258dd91 · outbound

This paper cites Stable Diffusion V1-4.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Stable Diffusion V1-4

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:41.133781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e022a6f3-4907-4124-82bb-69c168da8add · outbound

This paper cites Harnessing LLM to attack LLM-guarded text-to-image models, 2024.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Harnessing LLM to attack LLM-guarded text-to-image models, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.971321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a0cd097-f404-4df1-8045-736caa94d5b4 · outbound

This paper cites PRJ: Perception–Retrieval–Judgement for Generated Im- ages.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation PRJ: Perception–Retrieval–Judgement for Generated Im- ages

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.734073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 82fea954-9730-4131-83f8-71fb521009a8 · outbound

This paper cites Bermano, Gal Chechik, and Daniel Cohen-Or.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Bermano, Gal Chechik, and Daniel Cohen-Or

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.576979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0dfd38ff-4fcc-4ecd-a844-fadced6e605a · outbound

This paper cites Unified concept editing in dif- fusion models, 2024.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Unified concept editing in dif- fusion models, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.402214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d820964-bbf4-4a64-b55e-73ad1b85070e · outbound

This paper cites RT-attack: Jailbreaking text-to-image models via random token, 2024.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation RT-attack: Jailbreaking text-to-image models via random token, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.246134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 60e79cb4-b9ac-43ee-b8eb-3f1843ac3d1c · outbound

This paper cites A comprehensive evaluation framework for deep model robustness.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation A comprehensive evaluation framework for deep model robustness

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:40.020828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f17f7327-3834-4370-8fc9-110f48343850 · outbound

This paper cites CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:30.653628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cff10742-0ac3-4f25-a823-d691efe49401 · outbound

This paper cites Detoxify, 2020.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Detoxify, 2020

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:39.894828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c30dd53a-47a2-4715-94e4-b646d0c680fb · outbound

This paper cites Denoising dif- fusion probabilistic models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Denoising dif- fusion probabilistic models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:39.731265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43d18d3d-9c78-425d-96b5-ef413592dae9 · outbound

This paper cites SafeText: Safe text-to-image models via aligning the text en- coder, 2025.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation SafeText: Safe text-to-image models via aligning the text en- coder, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:39.522459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e441cc9-1545-414d-9bbb-79211bccc011 · outbound

This paper cites Optimal control and filtering for hierarchical decision prob- lems with h ınfty constraint based on stackelberg strategy.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Optimal control and filtering for hierarchical decision prob- lems with h ınfty constraint based on stackelberg strategy

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:39.347088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a2b23db5-1b66-425a-bccb-6c5b34fe366f · outbound

This paper cites CogMorph: Cog- nitive morphing attacks for text-to-image models, 2025.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation CogMorph: Cog- nitive morphing attacks for text-to-image models, 2025

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:39.136193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96b2db9f-18fd-4df5-be38-249fcf7a4e8f · outbound

This paper cites SafeGen: Mitigating sexually explicit content generation in text-to-image models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation SafeGen: Mitigating sexually explicit content generation in text-to-image models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.945347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 530753f8-f3e3-4448-bb1b-c71fe8d952a0 · outbound

This paper cites BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:31.458929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe94069-521a-4401-9671-b154cc9c9e28 · outbound

This paper cites Re- visiting backdoor attacks against large vision-language mod- els from domain shift.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Re- visiting backdoor attacks against large vision-language mod- els from domain shift

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.733040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cb9f7893-f182-42ee-95f0-752afcaef785 · outbound

This paper cites T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:31.618529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 151435ef-9b65-4af7-9b32-be04a2ce2142 · outbound

This paper cites Lawrence Zitnick, and Piotr Doll ´ar.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Lawrence Zitnick, and Piotr Doll ´ar

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.573891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c431097-5725-4191-8c38-99b9389b279b · outbound

This paper cites Perceptual-sensitive gan for generating adversarial patches.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Perceptual-sensitive gan for generating adversarial patches

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.407918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9b68c8f7-ff0a-40ab-8322-2089cf3f455b · outbound

This paper cites Spatiotemporal attacks for embodied agents.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Spatiotemporal attacks for embodied agents

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.218530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation db60c617-1e9f-4ba9-8ff1-369539526bd4 · outbound

This paper cites Bias-based universal adver- sarial patch attack for automatic check-out.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Bias-based universal adver- sarial patch attack for automatic check-out

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:38.000619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 37afec21-fd77-433b-805b-a255d99f773f · outbound

This paper cites Training robust deep neural networks via adversarial noise propagation.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Training robust deep neural networks via adversarial noise propagation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:37.829662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1982fda3-23ac-437a-9089-7fd7ea48d7e7 · outbound

This paper cites X-adv: Physical adversarial object attacks against x-ray prohibited item detection.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation X-adv: Physical adversarial object attacks against x-ray prohibited item detection

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:32.171011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732ee33d-5524-43c8-8366-9ba96a376f27 · outbound

This paper cites Towards defend- ing multiple lp-norm bounded adversarial perturbations via gated batch normalization.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Towards defend- ing multiple lp-norm bounded adversarial perturbations via gated batch normalization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:37.612669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3f3a55c7-3121-4ec5-a812-15a548e7313a · outbound

This paper cites Exploring the rela- tionship between architecture and adversarially robust gen- eralization.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Exploring the rela- tionship between architecture and adversarially robust gen- eralization

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:37.437037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d4d8fe23-6cdb-47b3-b9e4-c733246331ea · outbound

This paper cites Towards Defending Multiple $$\ell p$$-Norm Bounded Adversarial Perturba- tions via Gated Batch Normalization.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Towards Defending Multiple $$\ell p$$-Norm Bounded Adversarial Perturba- tions via Gated Batch Normalization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:37.309988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ead45ba1-ca4c-4ead-ac0d-aa866f568297 · outbound

This paper cites T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:32.524690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f14cd5d-6bb2-45d5-817b-0ed73aad7664 · outbound

This paper cites Harnessing percep- tual adversarial patches for crowd counting.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Harnessing percep- tual adversarial patches for crowd counting

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:32.634872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f055d482-609d-4964-b76f-6388fbeb6401 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:32.726790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 518bf7e3-e5f0-47f6-b988-947ef77a2406 · outbound

This paper cites OpenAI Moderation.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation OpenAI Moderation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:37.132516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e8093e0-994f-498e-9c83-644d43cc520b · outbound

This paper cites SDXL: Improving latent diffusion models for high-resolution image synthesis, 2023.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation SDXL: Improving latent diffusion models for high-resolution image synthesis, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:36.968103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7293ee84-4f26-4dca-9c2c-4174da49f400 · outbound

This paper cites Safe-CLIP: Removing NSFW concepts from vision-and-language mod- els, 2024.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Safe-CLIP: Removing NSFW concepts from vision-and-language mod- els, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:36.758729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 38135e8b-c1c3-4e2d-a8db-7346bdbc1c96 · outbound

This paper cites SafeGuider: Robust and practical content safety control for text-to-image models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation SafeGuider: Robust and practical content safety control for text-to-image models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:36.585402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 17b10969-4787-478d-98a2-c7ab08bf6577 · outbound

This paper cites Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:48:34.536442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1139b3d6-c60b-42f8-ba16-15b5ace185cb · outbound

This paper cites Learning transferable visual models from natural language supervision, 2021.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Learning transferable visual models from natural language supervision, 2021

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:33.272426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4a51ddf-f048-4819-946c-02c8e0ae833e · outbound

This paper cites Can machines help us answering ques- tion 16 in datasheets, and In turn reflecting on inappropriate content?, 2022.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Can machines help us answering ques- tion 16 in datasheets, and In turn reflecting on inappropriate content?, 2022

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:36.364320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 68a41529-aabe-45f6-8ebf-f39d4fdc863e · outbound

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

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Safe latent diffusion: Mitigating in- appropriate degeneration in diffusion models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:36.158189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a934a30-2a0c-429c-a8a8-942d11468d9b · outbound

This paper cites Stable Diffusion V2-1.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Stable Diffusion V2-1

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.955793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 16f922bc-1cca-4dd9-b597-2f97ccada220 · outbound

This paper cites Robustart: Benchmarking robust- ness on architecture design and training techniques.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Robustart: Benchmarking robust- ness on architecture design and training techniques

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.760837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5187bb90-e472-41a5-ba2a-5d5b9ba8a3b8 · outbound

This paper cites Automatic Evaluation for Text- to-image Generation: Task-decomposed Framework, Dis- tilled Training, and Meta-evaluation Benchmark, 2024.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Automatic Evaluation for Text- to-image Generation: Task-decomposed Framework, Dis- tilled Training, and Meta-evaluation Benchmark, 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.599761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation baf890c3-81ca-4bdf-899a-5ed5fdad5654 · outbound

This paper cites Dual Attention Suppression At- tack: Generate Adversarial Camouflage in Physical World.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Dual Attention Suppression At- tack: Generate Adversarial Camouflage in Physical World

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.440750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c0624ec-43ef-472f-b609-52eadebb79eb · outbound

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

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation AEIOU: A unified defense framework against NSFW prompts in text-to-image models, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.267000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a7fb43ab-3a40-4445-842c-ef3ef69166f6 · outbound

This paper cites Srd: Reinforcement-learned se- mantic perturbation for backdoor defense in vlms.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Srd: Reinforcement-learned se- mantic perturbation for backdoor defense in vlms

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T05:48:33.792977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00d8bda8-afe0-494d-9806-ec5ab9197925 · outbound

This paper cites MMA-Diffusion: MultiModal Attack on Diffusion Models.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation MMA-Diffusion: MultiModal Attack on Diffusion Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:48:34.307378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 72cf3388-3c07-4d1e-a581-994688096c57 · outbound

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

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation SneakyPrompt: Jailbreaking text-to-image generative models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:35.124846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 55b1ff26-7523-417a-8a68-75ba4d445c51 · outbound

This paper cites Reasoning- Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models, 2025.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Reasoning- Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models, 2025

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:34.978596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2d01184e-ca29-47f0-b0c0-c59fdf938e40 · outbound

This paper cites PromptGuard: Soft prompt-guided unsafe content moderation for text-to-image models, 2025.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation PromptGuard: Soft prompt-guided unsafe content moderation for text-to-image models, 2025

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:34.864677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bc84559f-9693-4db9-9afd-8c08e9240304 · outbound

This paper cites Interpreting and im- proving adversarial robustness of deep neural networks with neuron sensitivity.

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation Interpreting and im- proving adversarial robustness of deep neural networks with neuron sensitivity

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:48:34.721961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 27ea5e29-0bad-4ee4-8757-31ec2f82e629 · inbound

Memory Enhanced Fractional-Order Dung Beetle Optimization for Photovoltaic Parameter Identification cites this paper.

Memory Enhanced Fractional-Order Dung Beetle Optimization for Photovoltaic Parameter Identification PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:32:12.968384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.