Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-23T05:47:38.650729Z
Paper Citation Record · LEDGER
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
As of 11 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 4 inbound Pith citation observations for arXiv:2501.03544.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:19:49.787939Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-16T09:10:47.387233Z
Reference resolution
62 of 62 outbound references displayed
- verified exact11
- verified fuzzy46
- unresolved4
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 92be672e-5ed5-47cb-914b-d9b352b41f7d · outbound
This paper cites Stable Diffusion V1-4.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Stable Diffusion V1-4
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.491646Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 64bec420-b234-4f0e-ae32-9bbbe7c5bd08 · outbound
This paper cites AI Porn Is Easy to Make Now. For Women, That’s a Nightmare.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models AI Porn Is Easy to Make Now. For Women, That’s a Nightmare
Reference 2
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-23T05:57:37.488089Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3b7b6c90-02ed-4543-a464-1e6023ee401a · outbound
This paper cites Spotting the Deepfakes in This Year of Elections: How AI Detection Tools Work and Where They Fail.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Spotting the Deepfakes in This Year of Elections: How AI Detection Tools Work and Where They Fail
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.495188Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e4ae70d2-899f-4e79-8494-f327d80f656c · outbound
This paper cites Text-to-image AI Models Can Be Tricked Into Generating Disturbing Images.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Text-to-image AI Models Can Be Tricked Into Generating Disturbing Images
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.502692Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c2573ebb-86ca-4e32-ae46-882c11191ce9 · outbound
This paper cites AI-created Child Sexual Abuse Images ‘Threaten to Overwhelm Internet’.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models AI-created Child Sexual Abuse Images ‘Threaten to Overwhelm Internet’
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.506150Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 67fa67c3-671c-45e3-85bf-916134c0b9ba · outbound
This paper cites 2024: The Election Year of Deepfakes, Doubts and Disinfor- mation?.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models 2024: The Election Year of Deepfakes, Doubts and Disinfor- mation?
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.498952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 5185e3ec-5240-44a5-89a4-dea1c415e47e · outbound
This paper cites Erasing Concepts from Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Erasing Concepts from Diffusion Models
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.633267Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 217db278-1a10-47e6-a4d0-1ca0c1b0ef6e · outbound
This paper cites Unified Concept Editing in Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unified Concept Editing in Diffusion Models
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.514740Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f3f287ec-3003-4801-af96-7397fcd9425e · outbound
This paper cites SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.518687Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0ee3fc99-c9b9-4020-96ff-ee369b5bb5ba · outbound
This paper cites Direct Unlearning Optimization for Robust and Safe Text-to-Image Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.719333Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 041ace09-39bd-4075-ab89-267f62214d1e · outbound
This paper cites Stable Diffusion V2-1.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Stable Diffusion V2-1
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.522753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation cbb9cf48-01c8-4851-bf70-8f32ffc9d736 · outbound
This paper cites Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.753693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a4e04ab6-58f7-42c5-8e4d-0ef1b1e919de · outbound
This paper cites Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.733101Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1cb2af2d-8426-49a2-a6b4-5454eb969e07 · outbound
This paper cites NSFW Text Classifier on Hugging Face.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models NSFW Text Classifier on Hugging Face
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.574104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation eb2466aa-027c-4a2d-afc7-39f02da08ff6 · outbound
This paper cites Safety Checker.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Safety Checker
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.585935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation eb45498b-04ee-44af-a005-b7076b64bf5c · outbound
This paper cites Universal Prompt Optimizer for Safe Text-to-image Generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Universal Prompt Optimizer for Safe Text-to-image Generation
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.551128Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 73952674-afe0-4b31-9343-bb99a0fb7319 · outbound
This paper cites GPT Documentation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models GPT Documentation
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.661583Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 4451e925-8204-449a-8879-fb6c6e8e3092 · outbound
This paper cites DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.665247Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation b017c767-edab-4e9c-93b8-74cca17dae5e · outbound
This paper cites SDEdit: Guided Image Synthesis and Editing with Stochastic Differ- ential Equations.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models SDEdit: Guided Image Synthesis and Editing with Stochastic Differ- ential Equations
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.669171Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation fc6d5212-b794-4445-a92a-d0ecb7f9c57b · outbound
This paper cites Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-image Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-image Models
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.658127Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation dd3079c0-16f8-420b-85a9-728cb0eefe7e · outbound
This paper cites Towards Understanding Unsafe Video Generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Towards Understanding Unsafe Video Generation
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.761637Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 32a1b4ba-4905-4144-891a-bb22e747315a · outbound
This paper cites Latent Guard: a Safety Framework for Text-to-image Generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Latent Guard: a Safety Framework for Text-to-image Generation
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.746954Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6098cb20-d5ad-41ec-9d3b-1c2a86b5154d · outbound
This paper cites Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.651647Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 29ff2549-263c-4149-98cf-fbe9188884ad · outbound
This paper cites Denoising Diffusion Probabilistic Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Denoising Diffusion Probabilistic Models
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.654774Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 893e52c0-311e-49df-b585-79f15962dd51 · outbound
This paper cites High- resolution Image Synthesis with Latent Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models High- resolution Image Synthesis with Latent Diffusion Models
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.672781Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 23a46255-d7cd-443f-b42d-acc007a28fb6 · outbound
This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.623866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 2a04c0ca-4fa9-4bef-b4a7-f9af7ca0f02c · outbound
This paper cites LAION-5B: an Open Large-scale Dataset for Training Next Generation Image-text Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models LAION-5B: an Open Large-scale Dataset for Training Next Generation Image-text Models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.626866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f6c1c8b8-4260-4b43-a7ff-bb7482966d49 · outbound
This paper cites Diffusion Lens: Interpreting Text Encoders in Text-to-image Pipelines.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Diffusion Lens: Interpreting Text Encoders in Text-to-image Pipelines
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.630083Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6c641b21-b930-4fec-9bc4-99d4f0a03be0 · outbound
This paper cites The Prompt Report: A Systematic Survey of Prompt Engineering Techniques.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Reference 29
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:52:37.738880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 2264cda4-9d7e-4f82-8923-0919a98e9530 · outbound
This paper cites Safety system messages in llm.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Safety system messages in llm
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.643590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 335a6757-6285-41a9-9492-c49c0b40b1e2 · outbound
This paper cites On Prompt-driven Safeguarding for Large Language Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models On Prompt-driven Safeguarding for Large Language Models
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.648055Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c0a89f31-0d11-4873-9237-c2b889bce385 · outbound
This paper cites The Power of Scale for Parameter-efficient Prompt Tuning.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models The Power of Scale for Parameter-efficient Prompt Tuning
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.616960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation b3a8f481-c598-4df8-8ced-fe166e59a966 · outbound
This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Prefix-Tuning: Optimizing Continuous Prompts for Generation
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.613356Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a4a4aea7-444f-49d3-b3f8-5ed3d2cc8b7f · outbound
This paper cites NSFW Data Scraper.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models NSFW Data Scraper
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.606569Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ff86f842-9168-4666-a724-05305088c884 · outbound
This paper cites GPT-4o Mini: Advancing Cost-efficient Intelligence.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models GPT-4o Mini: Advancing Cost-efficient Intelligence
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.610135Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e01dea7d-036b-4ce2-b63c-d4f8eb6fc97a · outbound
This paper cites Scholar gpt.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Scholar gpt
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.595955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3d783113-5167-4fab-af27-0427bc39b37f · outbound
This paper cites GPT-4 Technical Report.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models GPT-4 Technical Report
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:52:37.701894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f3be6d0d-f11c-490e-b460-3b306ba84881 · outbound
This paper cites Microsoft COCO: Common Objects in Context.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Microsoft COCO: Common Objects in Context
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:52:37.687145Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a3039af8-5b2f-4290-80c3-aeaabf51e71c · outbound
This paper cites Inaproppriate Image Prompts (I2P).
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Inaproppriate Image Prompts (I2P)
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.599511Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation db94cd85-a9fb-450d-ac66-21ed95527b51 · outbound
This paper cites SneakyPrompt: Jailbreaking Text-to-image Generative Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models SneakyPrompt: Jailbreaking Text-to-image Generative Models
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.603300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 46ba181d-f274-48fc-bb39-dafcd4400e73 · outbound
This paper cites MMA-Diffusion: MultiModal Attack on Diffusion Models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models MMA-Diffusion: MultiModal Attack on Diffusion Models
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.620427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6c58fbc6-59df-49de-ba00-f16fef481aa2 · outbound
This paper cites Learning Transferable Visual Models From Natural Language Supervi- sion.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Learning Transferable Visual Models From Natural Language Supervi- sion
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.636574Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bc50cf4c-d762-43c8-b6b5-d0eeca2848fd · outbound
This paper cites The Unreasonable Effectiveness of Deep Features as a Perceptual Metric.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.577687Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 73147fe8-15b1-4ff9-9e21-b54e97705891 · outbound
This paper cites SafeGen-Pretrained-Weights.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models SafeGen-Pretrained-Weights
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.589043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 9a406cbd-405f-48c6-9e48-3e159fda6b23 · outbound
This paper cites Diffusers: State-of-the-art diffusion models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Diffusers: State-of-the-art diffusion models
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.570590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0e61c656-bc50-47e7-92cc-e2ddff2f13ee · outbound
This paper cites AlignGuard: Scalable Safety Alignment for Text-to-Image Generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
Reference 46
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T05:52:37.695699Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1b2c5cdc-e61f-490e-a433-3d6b3a64ac91 · outbound
This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Reference 47
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:52:37.725725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 860938b0-fc8e-41da-a7df-f8044c4c9804 · outbound
This paper cites Unified concept editing in diffusion models.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unified concept editing in diffusion models
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.567080Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ecb94e11-c4a9-4cd3-9d9c-6dac33e52083 · outbound
This paper cites Safe Stable Diffusion.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Safe Stable Diffusion
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.582262Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a511c049-9585-4864-92ee-0503273dc4ca · outbound
This paper cites Universal prompt optimizer for safe text-to-image generation.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Universal prompt optimizer for safe text-to-image generation
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.554695Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 037a4afb-a041-4916-9095-67e9c755aa60 · outbound
This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Reference 51
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:52:37.708818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 92f8a4ab-ac67-4d7e-92c4-2a84359a5b75 · outbound
This paper cites DeepFloyd IF.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models DeepFloyd IF
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.558292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 18bdccc7-e492-4895-b920-bbb6915c8710 · outbound
This paper cites • NSFW-200: To compensate for the shortcomings of I2P dataset in pornographic data, we use the NSFW dataset from [40] for the sexual category.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models • NSFW-200: To compensate for the shortcomings of I2P dataset in pornographic data, we use the NSFW dataset from [40] for the sexual category
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.547720Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 73845a3b-9bbb-4457-addc-faef71f01f6b · outbound
This paper cites safe” category or one of several “unsafe.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models safe” category or one of several “unsafe
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.562974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0b0342df-cfd2-450e-aea7-db93260f98bc · outbound
This paper cites According to our taxonomy, these baselines can be divided into three groups: (1)N/A: where the original SD serves as the control group without any protective measures.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models According to our taxonomy, these baselines can be divided into three groups: (1)N/A: where the original SD serves as the control group without any protective measures
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.592713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a69a872b-734d-456a-9c26-b62057813194 · outbound
This paper cites laion-aesthetics v2 5+.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models laion-aesthetics v2 5+
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.639840Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 32006710-4bc5-40c7-b9e7-ba10c7000ba6 · outbound
This paper cites Figure 6 illustrates the variations in images generated by the model with embeddings trained using different values ofλ.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Figure 6 illustrates the variations in images generated by the model with embeddings trained using different values ofλ
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.544427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f1526055-98a7-4404-b997-86bac1f3e7df · outbound
This paper cites an unresolved cited work.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unresolved cited work
Reference 58
- Resolution
- unresolved
- raw_fallback, observed 2026-05-23T05:57:37.533379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 23c51e80-31b6-4911-873c-23c43fd49ae2 · outbound
This paper cites an unresolved cited work.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-05-23T05:57:37.529950Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 7e8a40e8-7cd1-4650-b4d6-0b81dd5957f0 · outbound
This paper cites an unresolved cited work.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unresolved cited work
Reference 60
- Resolution
- unresolved
- raw_fallback, observed 2026-05-23T05:57:37.526513Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 92864f25-f10e-46ab-abd4-a89bee12667d · outbound
This paper cites an unresolved cited work.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models Unresolved cited work
Reference 61
- Resolution
- unresolved
- raw_fallback, observed 2026-05-23T05:57:37.537017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6b1194b7-366d-4e08-8301-02cd77293147 · outbound
This paper cites laion-aesthetics v2 5+.
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models laion-aesthetics v2 5+
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T05:57:37.540960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Pith citing papers
Observation b1d6e574-8f83-4d08-b928-e2e245f2caff · inbound
Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression cites this paper.
Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:19:49.787939Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 83433343-b983-4289-ba93-fe5dc134f82a · inbound
Do Concept Replacement Techniques Really Erase Unacceptable Concepts? cites this paper.
Do Concept Replacement Techniques Really Erase Unacceptable Concepts? PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:03:22.530957Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b062156-6f47-4033-a5d3-e93611e785e3 · inbound
SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation cites this paper.
SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T09:10:47.388809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 5e9c3278-dafb-49a2-b768-4a064f345c3a · inbound
Dynamic Eraser for Guided Concept Erasure in Diffusion Models cites this paper.
Dynamic Eraser for Guided Concept Erasure in Diffusion Models PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T02:44:43.880022Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.