Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling | Paper Citation Record

Observation 7213e407-a76a-4499-98d8-1eff255774e3 · outbound

This paper cites Celebrity classifier, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Celebrity classifier, 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:31.309743Z

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 52b76d30-af06-4380-ab6c-0093d1036098 · outbound

This paper cites Surrogateprompt: Bypassing the safety filter of text-to-image models via substitution.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Surrogateprompt: Bypassing the safety filter of text-to-image models via substitution

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:31.130812Z

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 bcc243bd-3f42-4d95-a364-1966322f6252 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Rank analysis of incomplete block designs: I

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:17.480819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ddc307-4acc-4a61-979d-5aec513355aa · outbound

This paper cites Towards evaluating the robustness of neural networks.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Towards evaluating the robustness of neural networks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.954023Z

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 d8a54403-6929-4971-924e-d969aef0812a · outbound

This paper cites Efficient black-box adversarial attacks via bayesian optimization guided by a function prior.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Efficient black-box adversarial attacks via bayesian optimization guided by a function prior

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.731532Z

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 f4b6bd00-7fad-41a3-9d6a-df6070c773fb · outbound

This paper cites Nsfw classifier, 2020.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Nsfw classifier, 2020

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.541079Z

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 2607205e-a345-4de2-aa19-8657327b69d4 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:17.851622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 302a729b-f1e9-4599-b678-568309be19f4 · outbound

This paper cites Prompt- ing4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Prompt- ing4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.350547Z

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 09c609b7-e181-448e-bb7a-fe6c85f3a22c · outbound

This paper cites Ai, governance and ethics: Global perspectives.Deakin University, 2022.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Ai, governance and ethics: Global perspectives.Deakin University, 2022

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.195262Z

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 bd1da015-bdc2-4b01-b211-9c0d292871b5 · outbound

This paper cites DiffZOO: A purely query-based black-box attack for red-teaming text-to-image generative model via zeroth order optimization.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling DiffZOO: A purely query-based black-box attack for red-teaming text-to-image generative model via zeroth order optimization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:30.011805Z

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 e67544bf-ce66-444a-bb28-aef262b2cd78 · outbound

This paper cites Harnessing LLM to Attack LLM-Guarded Text-to-Image Models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Harnessing LLM to Attack LLM-Guarded Text-to-Image Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:18.229670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7ffd36d-b273-4386-b1f0-8e5745dab2f0 · outbound

This paper cites Diffusion models beat gans on image synthesis.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Diffusion models beat gans on image synthesis

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:29.815910Z

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 477227f5-33d7-44e2-ab34-fed481a1730b · outbound

This paper cites Fuzz-testing meets llm-based agents: An automated and efficient framework for jailbreaking text-to-image generation models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Fuzz-testing meets llm-based agents: An automated and efficient framework for jailbreaking text-to-image generation models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:29.646645Z

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 fbcc5485-8414-4efd-9802-e7b7a685f6fe · outbound

This paper cites Boosting adversarial attacks with momentum.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Boosting adversarial attacks with momentum

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:29.475005Z

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 4f7466b9-fadd-4353-bd4f-fec8b7f93bc9 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Scaling rectified flow transformers for high-resolution image synthesis

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:18.643073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50b48699-5fc3-4594-b4b8-2746fffee5bd · outbound

This paper cites Erasing concepts from diffusion models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Erasing concepts from diffusion models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:29.331992Z

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 d26723c8-9118-4275-900c-63bbd3b3025c · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:18.819612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a49ab0d-39c9-47a6-8212-c417de26dce8 · outbound

This paper cites Nsfw words list, 2020.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Nsfw words list, 2020

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:29.140756Z

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 240eb587-21fe-4047-8a0d-aaf97b6f29df · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Lora: Low-rank adaptation of large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:18.920350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb62a34-8a82-465c-a8cf-cbb6bfd04362 · outbound

This paper cites SafeText: Safe Text-to-image Models via Aligning the Text Encoder.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling SafeText: Safe Text-to-image Models via Aligning the Text Encoder

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:46:22.914668Z

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 5e76d815-3402-4269-a9ae-51d7d23df193 · outbound

This paper cites Perception-guided jailbreak against text-to-image models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Perception-guided jailbreak against text-to-image models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.087710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a65f958-fe1f-4e54-95f9-0879c7fab595 · outbound

This paper cites Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.142147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4401f9c-69e9-4f5b-806f-e65aa1952635 · outbound

This paper cites Adam: A method for stochastic optimization.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Adam: A method for stochastic optimization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:28.807742Z

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 2a8feb87-0ce8-47a5-8314-3684fe06096d · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Ablating concepts in text-to-image diffusion models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.268964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0506285b-9277-46b0-bd7a-e24fe4bd2c9c · outbound

This paper cites Clip-based nsfw detector, 2023.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Clip-based nsfw detector, 2023

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:28.555116Z

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 e0f17040-82a2-4d07-bf21-dabba4925994 · outbound

This paper cites Leonardo.ai, 2022.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Leonardo.ai, 2022

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:28.287919Z

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 c241e591-9701-4438-9c98-d322404545c0 · outbound

This paper cites ART: Automatic red-teaming for text-to-image models to protect benign users.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling ART: Automatic red-teaming for text-to-image models to protect benign users

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:28.064581Z

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 a55cf6fc-1b2c-45aa-82ed-46267a11149d · outbound

This paper cites Nsfw text classifier, 2022.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Nsfw text classifier, 2022

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:27.833579Z

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 0b2ac8c0-6674-4d39-b19a-fb3a38f93b8b · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Safegen: Mitigating sexually explicit content generation in text-to-image models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:27.602149Z

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 cc93bfd3-a209-4e05-aaa3-9125c7d85765 · outbound

This paper cites Token-level constraint boundary search for jailbreaking text-to-image models.arXiv preprint arXiv:2504.11106, 2025.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Token-level constraint boundary search for jailbreaking text-to-image models.arXiv preprint arXiv:2504.11106, 2025

Reference 30

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:46:22.760888Z

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 a96a5cb0-198f-49a8-b559-c889ee5ccfc7 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.818242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56c8239-7242-4e50-9f38-e832e98b5b1d · outbound

This paper cites AlignGuard: Scalable Safety Alignment for Text-to-Image Generation.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling AlignGuard: Scalable Safety Alignment for Text-to-Image Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.898008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fcb33dd-1bf0-4fbb-b678-57ae94190f53 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:19.995687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a922576-fcbd-49d4-9ef3-ec890401d18a · outbound

This paper cites FLIRT: Feedback loop in-context red teaming.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling FLIRT: Feedback loop in-context red teaming

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:27.366287Z

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 f1308b71-6a34-489f-9188-096c7e89bb84 · outbound

This paper cites Improving robustness of 3d point cloud recognition from a fourier perspective.Advances in Neural Information Processing Systems, 37:68183–68210, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Improving robustness of 3d point cloud recognition from a fourier perspective.Advances in Neural Information Processing Systems, 37:68183–68210, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:27.190137Z

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 467b4409-30d4-4c1b-9694-2dad6d3548e5 · outbound

This paper cites Isometric 3d adversarial examples in the physical world.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Isometric 3d adversarial examples in the physical world

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:26.900403Z

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 3cff4872-a4db-43ca-af70-fab9448f06dd · outbound

This paper cites T2vsafetybench: Evaluating the safety of text-to-video generative models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling T2vsafetybench: Evaluating the safety of text-to-video generative models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:26.695208Z

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 69bdedcb-bf52-4e33-a01a-823f00e69bd5 · outbound

This paper cites Midjourney, 2022.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Midjourney, 2022

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:26.552820Z

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 c2945038-ef4b-4fd4-b31f-9bae3ac5353b · outbound

This paper cites Google chief admits ‘biased’ ai tool’s photo diversity offended users, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Google chief admits ‘biased’ ai tool’s photo diversity offended users, 2024

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:26.350446Z

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 40669cae-625e-4c0b-95cc-e3a97055aa21 · outbound

This paper cites Simple open- vocabulary object detection.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Simple open- vocabulary object detection

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:20.472709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e66aadb-8579-4289-816f-703d3db17b14 · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:20.607480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c340ee-1281-4093-82eb-486d975db18b · outbound

This paper cites Nudenet, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Nudenet, 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:26.195613Z

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 e29ea114-a80f-483c-bc6b-611cd3d7f48c · outbound

This paper cites Dall-e 3, 2023.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Dall-e 3, 2023

Reference 43

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T13:46:25.903404Z

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 071b87ad-f2a8-47fd-9488-db8bb42ca730 · outbound

This paper cites Gpt-4o, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Gpt-4o, 2024

Reference 44

Resolution: parse uncertain; no resolver link, observed 2026-08-07T13:46:20.815343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70071a16-0f91-4d37-849a-69ccbbfe0137 · outbound

This paper cites Direct unlearning optimization for robust and safe text-to-image models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Direct unlearning optimization for robust and safe text-to-image models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:25.742889Z

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 ee6a0495-1b09-40e9-b9ee-95cc7135e784 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:25.446553Z

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 6e1ac51a-2cf5-426b-8df5-e39f2ddf89fc · outbound

This paper cites Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:25.166876Z

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 5a9417ca-ed68-4a39-8c97-2a73725cf61b · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Learning transferable visual models from natural language supervision

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:20.994286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9e8a497-3a7b-43f8-b2d4-910d6cfe83a2 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Direct preference optimization: Your language model is secretly a reward model

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.053115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 069feabf-56b7-48ad-bcbb-71e4bc0b117f · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Red-Teaming the Stable Diffusion Safety Filter

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.103762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef9f718a-01fe-4bfa-89c3-a811671efda5 · outbound

This paper cites Classification algorithm for skin color (casco): A new tool to measure skin color in social science research.Social Science Quarterly, 104(2):168–179, 2023.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Classification algorithm for skin color (casco): A new tool to measure skin color in social science research.Social Science Quarterly, 104(2):168–179, 2023

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:24.962779Z

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 61c2704e-383b-41d1-b3ef-2b81fb9a26ca · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling High-resolution image synthesis with latent diffusion models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.207599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31582233-3665-4da0-9446-2f272ad18f63 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.237818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e0f4d0-d0a0-4408-9e1a-0b54fd0edc2d · outbound

This paper cites an unresolved cited work.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:46:24.780866Z

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 88ad7575-0e1c-4f98-9c49-18db54aedb42 · outbound

This paper cites Intriguing properties of neural networks.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Intriguing properties of neural networks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.369807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6738f7f1-63f0-41e7-a1a0-28876b497cf4 · outbound

This paper cites Ring-a-bell! how reliable are concept removal methods for diffusion models? In International Conference on Learning Representations, 2024.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Ring-a-bell! how reliable are concept removal methods for diffusion models? In International Conference on Learning Representations, 2024

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:24.616897Z

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 d589ca16-96bc-435f-b1a4-b1300211dcfe · outbound

This paper cites The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breacheswithout adjusting finetuning pipeline.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breacheswithout adjusting finetuning pipeline

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:24.400324Z

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 65027b5e-da50-4a00-9771-6d7a9b5c45cd · outbound

This paper cites Mma-diffusion: Multimodal attack on diffusion models.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Mma-diffusion: Multimodal attack on diffusion models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.505094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d908c12-fb10-4f01-bd53-86196e7bf2f3 · outbound

This paper cites Guardt2i: Defending text-to-image models from adversarial prompts.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Guardt2i: Defending text-to-image models from adversarial prompts

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:24.220464Z

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 f5c7171d-2b61-4b9f-bdbf-32773b1389b9 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Sneakyprompt: Jailbreaking text-to-image generative models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.617031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e8d408-10f4-4b86-a1f4-51e7ddae20af · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Safree: Training-free and adaptive guard for safe text-to-image and video generation

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:24.028683Z

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 2c06bf45-5431-490c-a162-0ea182b21ecb · outbound

This paper cites Generalization bound and new algorithm for clean-label backdoor attack.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Generalization bound and new algorithm for clean-label backdoor attack

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:23.873655Z

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 b0a9bb0f-61ec-4674-89ef-bc34fe84c2aa · outbound

This paper cites Reason2attack: Jailbreaking text-to-image models via llm reasoning.arXiv preprint arXiv:2503.17987, 2025.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Reason2attack: Jailbreaking text-to-image models via llm reasoning.arXiv preprint arXiv:2503.17987, 2025

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.781190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8faed6ec-0b2e-4ffc-9dca-687387e16f30 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Forget-me-not: Learning to forget in text-to-image diffusion models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:23.682527Z

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 154b2969-cc2c-41e1-9b9b-22de165de71c · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Defensive unlearning with adversarial training for robust concept erasure in diffusion models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:23.502622Z

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 15b7c14f-59f1-4b63-b7fc-798547a57951 · outbound

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

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:23.312372Z

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 8ab008de-a947-42c6-ae96-463eaa733b6a · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Open-Sora: Democratizing Efficient Video Production for All

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:21.978840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19c51780-bba0-4ba0-ae09-2d0618bf543b · outbound

This paper cites Toward availability attacks in 3d point clouds.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling Toward availability attacks in 3d point clouds

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:46:23.130581Z

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 224e5c65-dd55-4502-a2fe-ba86fb6bd002 · outbound

This paper cites A pilot study of query-free adversarial attack against stable diffusion.

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling A pilot study of query-free adversarial attack against stable diffusion

Reference 69

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:46:22.366927Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers