Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models | Paper Citation Record

Observation 02c3b149-e711-4e9f-b4f9-54b4e28b75d7 · outbound

This paper cites GPT-4 Technical Report.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:15.947995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd15361-39cc-430a-9b77-130ad3f1c618 · outbound

This paper cites Elijah: Eliminating backdoors injected in diffusion models via distribution shift.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Elijah: Eliminating backdoors injected in diffusion models via distribution shift

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.897375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0e15bbd9-5082-4a9d-9b0a-e90da71f9b81 · outbound

This paper cites Defense-prefix for pre- venting typographic attacks on clip.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Defense-prefix for pre- venting typographic attacks on clip

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.880241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8652d655-23e9-48d5-a5b0-0e03519bbee9 · outbound

This paper cites In- structpix2pix: Learning to follow image editing instructions.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models In- structpix2pix: Learning to follow image editing instructions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.863071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ec4da44d-6208-4b9a-be51-1f4b2a33fdf3 · outbound

This paper cites Controllable generation with text-to-image diffusion models: A survey.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Controllable generation with text-to-image diffusion models: A survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:15.986038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a36bde21-ca20-4645-84da-095867d5f8f4 · outbound

This paper cites Trojdiff: Trojan at- tacks on diffusion models with diverse targets.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Trojdiff: Trojan at- tacks on diffusion models with diverse targets

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:15.992611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec6bbc9-f0e4-4517-85ff-7d68f2b3b65f · outbound

This paper cites Rbformer: improve adversarial robustness of trans- former by robust bias.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Rbformer: improve adversarial robustness of trans- former by robust bias

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.830272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation efe0e062-367b-4ca2-be35-99b0f8466608 · outbound

This paper cites Un- veiling typographic deceptions: Insights of the typographic vulnerability in large vision-language model.European Con- ference on Computer Vision (ECCV), 2024.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Un- veiling typographic deceptions: Insights of the typographic vulnerability in large vision-language model.European Con- ference on Computer Vision (ECCV), 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.813758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a3a5a015-2408-493d-870a-f6109ce08919 · outbound

This paper cites Villan- diffusion: A unified backdoor attack framework for diffu- sion models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Villan- diffusion: A unified backdoor attack framework for diffu- sion models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.795940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 16e1dc5d-bbac-4df9-99be-1d86e7b699c6 · outbound

This paper cites Style injec- tion in diffusion: A training-free approach for adapting large- scale diffusion models for style transfer.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Style injec- tion in diffusion: A training-free approach for adapting large- scale diffusion models for style transfer

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.779803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9d9acdc3-f871-4b96-85d0-ce93883dfc4d · outbound

This paper cites Instructblip: Towards general- purpose vision-language models with instruction tuning,.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Instructblip: Towards general- purpose vision-language models with instruction tuning,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.035929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e05161cf-4914-4abd-8678-1f1d68a22132 · outbound

This paper cites Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language mod- els.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language mod- els

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.752409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2917006e-fb9a-409d-99d4-e0e4a1009d8c · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.736563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0c41b359-e9af-422b-8fca-b3ff5eae6d77 · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.054907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be1fb8b-9bcd-4c1e-ad14-8c4871f8c365 · outbound

This paper cites Generative adversarial networks.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Generative adversarial networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.063958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7930752-df99-4fad-b256-ba8d862dca48 · outbound

This paper cites A Survey on Responsible Generative AI: What to Generate and What Not.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models A Survey on Responsible Generative AI: What to Generate and What Not

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.069137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8ba173-6825-4b65-b867-427842bf5224 · outbound

This paper cites Detoxify.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Detoxify

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.706588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation eebffb7d-1594-474f-a07f-2d6b85a74a38 · outbound

This paper cites Defending against Backdoor Attack on Deep Neural Networks.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Defending against Backdoor Attack on Deep Neural Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.079816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bd09f48-55c7-4aa7-a65b-0af1229f569b · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.690423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4ee3f535-3742-4566-bde3-bb6122d1ba35 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Denoising dif- fusion probabilistic models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.092015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 556bce85-0274-4106-8ef4-9007da1ab1df · outbound

This paper cites All but one: Surgical concept erasing with model preservation in text-to- image diffusion models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models All but one: Surgical concept erasing with model preservation in text-to- image diffusion models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.662419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0481bf68-d92a-4e53-84db-4cc62e665811 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.103292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5ad5d92-219f-4c07-8b82-ece074facc03 · outbound

This paper cites Progressive Growing of GANs for Improved Quality, Stability, and Variation.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Progressive Growing of GANs for Improved Quality, Stability, and Variation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.109298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70d9bd6f-303d-43ab-bc83-c483a9a15efe · outbound

This paper cites Auto-Encoding Variational Bayes.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Auto-Encoding Variational Bayes

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.116002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f5ceb6-770f-4805-883a-6b85eeaebe98 · outbound

This paper cites Self-discovering interpretable diffusion latent di- rections for responsible text-to-image generation.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Self-discovering interpretable diffusion latent di- rections for responsible text-to-image generation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.644039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3dd086a4-7e79-471b-ab56-56afba6db1ab · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.137150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71f0f88a-8fbf-4865-a174-bfb8436f0712 · outbound

This paper cites Spd-ddpm: Denoising diffu- sion probabilistic models in the symmetric positive definite space.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Spd-ddpm: Denoising diffu- sion probabilistic models in the symmetric positive definite space

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.626817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e1d08a69-acfa-4ea1-9b94-ef572a375614 · outbound

This paper cites Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.152540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bc0d17b-7152-4eb6-af9e-3b002e5dac2c · outbound

This paper cites Which model generated this image? a model- agnostic approach for origin attribution.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Which model generated this image? a model- agnostic approach for origin attribution

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.607534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2ccc9a99-8687-48b0-9a78-b768756d6e54 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Improved Baselines with Visual Instruction Tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.165369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 467148d4-0fec-4a41-84a1-ba0a941534a0 · outbound

This paper cites Visual Instruction Tuning.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Visual Instruction Tuning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.171091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcd2f6c9-6a9c-468f-8eb5-57078ab22787 · outbound

This paper cites Latent guard: a safety frame- work for text-to-image generation.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Latent guard: a safety frame- work for text-to-image generation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.590711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c05fc1f7-6df0-48dc-80aa-8acbf6ed9b58 · outbound

This paper cites Multimodal prag- matic jailbreak on text-to-image models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Multimodal prag- matic jailbreak on text-to-image models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.573013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 16392452-1f48-41ed-a583-505200cdc8f9 · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.195700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2435339a-a0c1-480a-a9b8-1a3770a8d3de · outbound

This paper cites Large-scale celebfaces attributes (celeba) dataset.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Large-scale celebfaces attributes (celeba) dataset

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.554589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a06b4bea-ebaa-42a4-a776-85fd4c93f603 · outbound

This paper cites Information constraints on auto-encoding variational bayes.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Information constraints on auto-encoding variational bayes

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.537226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a0275460-a58a-46f9-ac1a-58dd1529dece · outbound

This paper cites An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.518701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 198e468f-803d-4cee-a8a4-9e0d4bd57a69 · outbound

This paper cites Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.226826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2edfa60-77c8-47ce-934a-0d9a200ea5dd · outbound

This paper cites A holistic approach to undesired content detection in the real world.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models A holistic approach to undesired content detection in the real world

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.500221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7626b988-ae74-4559-bbe6-3495c130d857 · outbound

This paper cites Dreamguider: Improved Training free Diffusion-based Conditional Generation.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Dreamguider: Improved Training free Diffusion-based Conditional Generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.247131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc9f6e0-757f-4237-bf2d-85d1d5b31f90 · outbound

This paper cites At-ddpm: Restoring faces degraded by atmospheric tur- bulence using denoising diffusion probabilistic models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models At-ddpm: Restoring faces degraded by atmospheric tur- bulence using denoising diffusion probabilistic models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.484104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d700a64a-157c-41d8-aa2a-db3adfbc0425 · outbound

This paper cites Contrastive denoising score for text-guided latent diffusion image editing.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Contrastive denoising score for text-guided latent diffusion image editing

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.467275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 11ea48a6-e231-4b9b-a4a2-dc2a461d0fb1 · outbound

This paper cites White-box Membership Inference Attacks against Diffusion Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models White-box Membership Inference Attacks against Diffusion Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.279099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 580454fc-c7ef-4465-8431-183ef9cace1e · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.285778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d24ded01-08f6-4477-91f8-1bef07cad98f · outbound

This paper cites Safe-clip: Removing nsfw concepts from vision-and-language models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Safe-clip: Removing nsfw concepts from vision-and-language models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.450071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f3fdfe8d-e283-48ab-8b0c-c59edf536f87 · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Learning transferable visual models from natural language supervision

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.431641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 79bb20c5-c338-4f24-9e9c-1e481733286c · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Learning transferable visual models from natural language supervi- sion

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.311262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e85317c9-32b4-4461-8a2b-435af4216843 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.317220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1901301-6bd3-469d-9c37-12a2c11fd13e · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Red-Teaming the Stable Diffusion Safety Filter

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.323922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c466172a-b985-4d33-9e9a-f83673b770fc · outbound

This paper cites Gener- ating diverse high-fidelity images with vq-vae-2.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Gener- ating diverse high-fidelity images with vq-vae-2

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.330422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8750fd41-ada9-4845-9cb1-f114b81e8ce3 · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models High-resolution image synthesis with latent diffusion models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.335821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d081260a-f4b2-496e-baf4-607ff318d5d7 · outbound

This paper cites Raising the Cost of Malicious AI-Powered Image Editing.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Raising the Cost of Malicious AI-Powered Image Editing

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.342958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c45e4a7-1f94-466f-ab87-acc99dd4d8b5 · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Deep unsupervised learning using nonequilibrium thermodynamics

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.349013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f961a41a-8ff6-474c-966e-e71c5bb3d1e8 · outbound

This paper cites Emu: Generative pretraining in multimodality.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Emu: Generative pretraining in multimodality

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.372299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e802768e-17cc-4a74-9438-ca6a84111fd6 · outbound

This paper cites Generative multimodal mod- els are in-context learners.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Generative multimodal mod- els are in-context learners

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.344759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b939e121-7ed5-4950-9f0e-5c6f072d5143 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models LLaMA: Open and Efficient Foundation Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.368896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba5fa7b-4918-401d-8eb1-8e8bb97917b7 · outbound

This paper cites Gcd-ddpm: A generative change detection model based on difference-feature guided ddpm.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Gcd-ddpm: A generative change detection model based on difference-feature guided ddpm

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.325116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 31f190b1-04b0-4372-8834-c35e970dbfb7 · outbound

This paper cites Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.386103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f7d067-0e3b-4097-8732-9a4e1e7fa217 · outbound

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Sneakyprompt: Jailbreaking text-to-image generative models

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.307571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cc4ba249-05ba-46ef-9cf8-ef0e9ef2fa5b · outbound

This paper cites IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:16.402465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c07f2aa-0b95-473c-8239-696ad4c3029f · outbound

This paper cites Inversion-based style transfer with diffusion models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Inversion-based style transfer with diffusion models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.291166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d2ec859b-e882-477c-a0fb-e1c0ca8066d8 · outbound

This paper cites Defensive unlearning with adversarial training for robust concept erasure in diffusion models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models Defensive unlearning with adversarial training for robust concept erasure in diffusion models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:17.274376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b5acb7ce-93af-49d7-8d8b-8ddd9a55b355 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 63

Resolution: malformed identifier; no resolver link, observed 2026-08-11T20:41:16.429938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers