Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions | Paper Citation Record

Observation fa65e9f8-c774-4ad2-91ff-c1c7cd13e955 · outbound

This paper cites https://medium.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://medium

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.264294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f90e3663-d161-4884-9ee4-157312844879 · outbound

This paper cites https://gnet- research.org/2023/11/13/for-the-lulz-ai- generated-subliminal-hate-is-a-new-challenge- in-the-fight-against-online-harm/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://gnet- research.org/2023/11/13/for-the-lulz-ai- generated-subliminal-hate-is-a-new-challenge- in-the-fight-against-online-harm/

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.236646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e11fc6e-767d-43a0-8b6b-660cc13f993b · outbound

This paper cites https://www.adl.org/resources/ hate-symbol/confederate-flag.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://www.adl.org/resources/ hate-symbol/confederate-flag

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.205451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8636eb7-cd0f-4bda-8fdf-c2618c994f8c · outbound

This paper cites https://openai.com/index/dall-e-2/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://openai.com/index/dall-e-2/

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.186379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dde478f7-e61e-484f-a536-3bf576e763ba · outbound

This paper cites https://ai.google.dev/gemini-api/docs.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://ai.google.dev/gemini-api/docs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.166603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca04f1a4-59a2-4e6c-9a18-4e1ccacfb145 · outbound

This paper cites https://cloud.google.com/vertex- ai/generative-ai/docs/gemini-v2.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://cloud.google.com/vertex- ai/generative-ai/docs/gemini-v2

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.150202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 80adc11a-3f25-440b-99b5-5b28a3feda24 · outbound

This paper cites https://cloud.google.com/ vision/docs/detecting-safe-search.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://cloud.google.com/ vision/docs/detecting-safe-search

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.130037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 691c62a7-d943-4396-a733-f188343eb325 · outbound

This paper cites https://openai.com/index/hello-gpt-4o.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://openai.com/index/hello-gpt-4o

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.109182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ac8cb876-6833-499b-bd00-f4d04fe857b4 · outbound

This paper cites https://openai.com/research/gpt-4v- system-card.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://openai.com/research/gpt-4v- system-card

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.093441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b603f6a5-b586-487c-b21b-bbae33390ee6 · outbound

This paper cites https://www.adl.org/ resources/hate-symbol/happy-merchant.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://www.adl.org/ resources/hate-symbol/happy-merchant

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.075863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 136c8510-5554-46be-8c1c-3fdcc9ef4b34 · outbound

This paper cites https://docs.opencv.org/3.4/ d4/d1b/tutorial_histogram_equalization.html.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://docs.opencv.org/3.4/ d4/d1b/tutorial_histogram_equalization.html

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.056274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation acc13bd6-c1a5-4977-8d02-fe57d8f4ec36 · outbound

This paper cites https://www.adl.org/resources/ hate-symbol/its-okay-be-white.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://www.adl.org/resources/ hate-symbol/its-okay-be-white

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.038233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa8c7079-482e-4015-ac32-2ea2f2a07dfa · outbound

This paper cites https://labelstud.io/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://labelstud.io/

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.018751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0471af1e-d18a-4fde-8512-c2e39b9c0545 · outbound

This paper cites https://huggingface.co/datasets/laion/ laion2B-en.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://huggingface.co/datasets/laion/ laion2B-en

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:38.002228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation da70c5cb-23f2-4b81-a16e-cf530a3feb72 · outbound

This paper cites https://laion.ai/blog/laion-5b/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://laion.ai/blog/laion-5b/

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.986869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bb0262fa-1d24-4c2a-828a-ea7669b563fb · outbound

This paper cites https://lexica.art/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://lexica.art/

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.967503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a1c7ffc-8e45-4a6a-8458-401aefea50cf · outbound

This paper cites https://learn.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://learn

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.949091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aec2e61c-f27e-4d75-9459-569a08e9fcb2 · outbound

This paper cites https://learn.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://learn

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.931769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a35cf7ae-26ca-4418-a197-b20ec5c137af · outbound

This paper cites https://midjourney.com/.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://midjourney.com/

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.910903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b4d43e1-ed9b-4df5-a491-06b97da62885 · outbound

This paper cites https://en.wikipedia.org/wiki/Misogyny.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://en.wikipedia.org/wiki/Misogyny

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.892316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9c3c016d-d9ff-4643-95c5-c7b1c64ff96a · outbound

This paper cites https://www.adl.org/resources/ hate-symbol/swastika.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://www.adl.org/resources/ hate-symbol/swastika

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.872258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 34bd2e2d-ceb3-4ae6-b25a-e703e0108544 · outbound

This paper cites https://platform.openai.com/docs/ guides/moderation.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://platform.openai.com/docs/ guides/moderation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.853491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a343d92-5266-463e-bb11-0fcc2aff8422 · outbound

This paper cites https://en.wikipedia.org/wiki/ Optical_illusion.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://en.wikipedia.org/wiki/ Optical_illusion

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.834310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d765928e-4e5f-4373-af5d-413406d28c09 · outbound

This paper cites https://huggingface.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://huggingface

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.817088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3ab09f71-85ff-47ea-819e-f4fd7366d796 · outbound

This paper cites https://stability.ai/news/stable- diffusion-public-release.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://stability.ai/news/stable- diffusion-public-release

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.790648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8c68454b-2ef5-4fef-be88-a94b2649b16b · outbound

This paper cites https://x.com/DiffusionPics/status/ 1703878083919347824/photo/1.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://x.com/DiffusionPics/status/ 1703878083919347824/photo/1

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.770649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a15bb35e-8e9b-4fca-b0ec-ed77fe74d653 · outbound

This paper cites https://www.adl.org/resources/hate- symbol/swastika.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions https://www.adl.org/resources/hate- symbol/swastika

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.749644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 372bda71-ed0d-4395-82e4-c3299076289b · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:24.795223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fa1c26c-b15b-4cbb-a3fd-4a61c7215956 · outbound

This paper cites SpaText: Spatio-Textual Representation for Con- trollable Image Generation.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions SpaText: Spatio-Textual Representation for Con- trollable Image Generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.731901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a7a400c-f80c-4d1a-b556-1685fe0897bf · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:25.130250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86a4b392-f72b-4dca-8ebe-ce1c5fac96bf · outbound

This paper cites Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.713376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dedf9e3a-9ec7-43d2-bb3a-a457192f8e21 · outbound

This paper cites Rehg, and Chao Zheng.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Rehg, and Chao Zheng

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.695145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 978874f7-3ba4-4a72-a237-7e77eceff154 · outbound

This paper cites Subverting the Jew- tocracy.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Subverting the Jew- tocracy

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.679558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4670feba-ae2a-4db1-94ac-2440fb56f748 · outbound

This paper cites Generic Attention- model Explainability for Interpreting Bi-Modal and Encoder- Decoder Transformers.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Generic Attention- model Explainability for Interpreting Bi-Modal and Encoder- Decoder Transformers

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.656487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 102d6ebf-ced6-4881-b1a7-fe371d4aa32d · outbound

This paper cites IllusionCAPTCHA: A CAPTCHA based on Visual Illusion.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions IllusionCAPTCHA: A CAPTCHA based on Visual Illusion

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:34:31.298920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eac89516-fb59-4140-8b55-0591fc57e4be · outbound

This paper cites Fleiss’ kappa statistic without paradoxes.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Fleiss’ kappa statistic without paradoxes

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.541709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 93a430e8-9f11-4b49-a718-a94ec62f7287 · outbound

This paper cites Measuring Nominal Scale Agreement Among Many Raters.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Measuring Nominal Scale Agreement Among Many Raters

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:37.200232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4fe1a3e1-2ce9-42bc-903c-9a5203af8fc4 · outbound

This paper cites Make-A-Scene: Scene- Based Text-to-Image Generation with Human Priors.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Make-A-Scene: Scene- Based Text-to-Image Generation with Human Priors

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:36.895234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f08493f7-8770-4fab-8c02-79a0d4b04565 · outbound

This paper cites An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:26.131295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506a91e9-d204-4e87-aff8-2ab7feb7adff · outbound

This paper cites Understanding and Detecting Hateful Content using Contrastive Learning.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Understanding and Detecting Hateful Content using Contrastive Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:26.252296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f518676d-e9cc-41f4-980b-a504f1baabbb · outbound

This paper cites Hal- lusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision- Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Hal- lusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision- Language Models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:36.641060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 540f87a9-35af-4383-9208-eeeed394eed0 · outbound

This paper cites LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:26.497339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f560e7b0-eef2-4c07-84fb-f2935996c012 · outbound

This paper cites CogVLM2: Visual Language Models for Image and Video Understanding.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions CogVLM2: Visual Language Models for Image and Video Understanding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:26.624192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a034d637-67dc-4be5-89f8-2f5bef351284 · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:36.374539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 87a0cb86-0ff1-40d4-bb37-f2cf3c1afe23 · outbound

This paper cites Llava-next: Improved reason- ing, ocr, and world knowledge, January 2024.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Llava-next: Improved reason- ing, ocr, and world knowledge, January 2024

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:36.194405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20a33a9f-8a50-4b01-be0b-92017c3e0686 · outbound

This paper cites Visual Instruction Tuning.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Visual Instruction Tuning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:36.006033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e4b49e86-cfb1-4912-add0-2ca3c3f1ebbc · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:27.174570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96618f7e-b14f-4842-acdb-1b997d5f3982 · outbound

This paper cites Safety Alignment for Vision Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Safety Alignment for Vision Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:27.336758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e99f8472-3b69-4564-91a6-e574840a735b · outbound

This paper cites From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Mod- els.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Mod- els

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:35.796109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 81a71fd9-969f-44ab-ab92-9b78a0de93a8 · outbound

This paper cites Bridging the Gap in Vision Language Models in Identifying Unsafe Con- cepts Across Modalities.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Bridging the Gap in Vision Language Models in Identifying Unsafe Con- cepts Across Modalities

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:35.678484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 38b197c8-50df-4a63-bbda-79d0f1c07270 · outbound

This paper cites On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learn- ing.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learn- ing

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:35.544777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c6a3f856-3ca6-446d-b3c3-62ed75f6db10 · outbound

This paper cites UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:27.797808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d49298aa-a5b4-4506-a8a8-e9445500abe8 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Learning Transferable Visual Models From Natural Language Supervision

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:35.387952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4579b1e2-4fab-4c1d-bab3-8c1d4c3056de · outbound

This paper cites High-Resolution Image Syn- thesis with Latent Diffusion Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions High-Resolution Image Syn- thesis with Latent Diffusion Models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:35.146246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 38a83140-adc5-433f-9cbe-d2b3b3269727 · outbound

This paper cites Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:34:30.891394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0010db0d-56c0-489a-b895-f237646a9e6e · outbound

This paper cites DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:34.959743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e1d6b8b-d049-4b45-833d-b81f7d510f87 · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:34.814899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9e722217-a78f-4df5-8d01-779faf826a48 · outbound

This paper cites IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:28.396066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae52288-29ef-4c81-a1e1-7e4717a83119 · outbound

This paper cites Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, and Li-Jia Li.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, and Li-Jia Li

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:34.645749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9f520b1f-6e98-43eb-9e39-15d02d9eaaaa · outbound

This paper cites Visualizing Data using t-SNE.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Visualizing Data using t-SNE

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:34.459957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a786c6ff-c205-49c3-b882-007f1beb3522 · outbound

This paper cites Rabiul Awal, Kenny Tsu Wei Choo, and Roy Ka-Wei Lee.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Rabiul Awal, Kenny Tsu Wei Choo, and Roy Ka-Wei Lee

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:34.253839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d51fcc23-5e77-44bd-8934-d6e3ef85481c · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:28.827989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a12f92-c08b-4b5a-8a1b-84056d419ef0 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions CogVLM: Visual Expert for Pretrained Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:28.913695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81082d14-8c05-41f1-92c3-3b034346f7f2 · outbound

This paper cites Le, Ed H.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Le, Ed H

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:33.988572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 00dff766-c9f0-4d6f-bae4-a56d8c40e2c2 · outbound

This paper cites Chi, Quoc V.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Chi, Quoc V

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:33.810455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 24ebe180-bcd9-47b1-acbb-eaa6cb396618 · outbound

This paper cites A Quantitative Approach to Understand- ing Online Antisemitism.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions A Quantitative Approach to Understand- ing Online Antisemitism

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:33.650004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9cd48675-3a9c-4606-b228-5b8b22c5900d · outbound

This paper cites Adding Conditional Control to Text-to-Image Diffusion Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Adding Conditional Control to Text-to-Image Diffusion Models

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:33.501192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f802cd54-a46a-435f-b20f-4dd23779009d · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:33.350161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 146890dd-4eeb-48e1-bbfe-099d407d78e3 · outbound

This paper cites IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:29.583103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6267b3ad-05da-4a09-b701-f8d71fc6916b · outbound

This paper cites Faot,” “Retd,.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Fa**ot,” “Ret**d,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:33.176741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f53d2550-4f39-4b49-b172-9cbe502ab2cf · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:32.975574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 535d3038-072a-4480-bde6-0e7025e9c04d · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:32.843576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 04d45965-9b3d-4d1b-baa3-6a913eef0e0f · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:32.625827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 26879c73-8e24-4869-ab42-2dd4e0c601da · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:32.393606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 36c933b6-8e3a-42e5-82ac-abd024ba62ec · outbound

This paper cites yes” or “no.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions yes” or “no

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:32.154912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f825c78-b547-452b-b1ee-ca81d4b3cfb8 · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:31.947684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a163ea47-9347-49ec-ab8f-be4107953f3d · outbound

This paper cites an unresolved cited work.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:34:31.734356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2aca0d3f-efb2-4caa-b580-84091a59c768 · outbound

This paper cites None”Input Image Gemini-2: “None.

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions None”Input Image Gemini-2: “None

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:34:31.554224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers