Paper Citation Record · LEDGER

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 46 inbound Pith citation observations for arXiv:2411.10414.

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

pith.paper-citation-record.v1
2411.10414 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:41:19.762055Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 46 of 46 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:57:21.997909Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-05T10:30:59.155257Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy1
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6bab6ff7-5926-4b4a-931b-4b97a1572bde · outbound

This paper cites GPT-4 Technical Report.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.611726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608c4cba-45bf-4837-a607-e7ac619bfe0a · outbound

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

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.687727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377965bc-55ef-4702-9e68-a9625ed67278 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Gemini: A Family of Highly Capable Multimodal Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.642602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7cc4230-c587-4dda-85db-f9c61cff8da6 · outbound

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

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.652833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8fa95f1-97ae-466a-a75f-73f812f06eb3 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.659949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5755abd-8543-4dfc-bb2a-6a97c54cc95f · outbound

This paper cites Scaling Laws for Neural Language Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Scaling Laws for Neural Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.664516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9c447c6-1fb2-46e7-bdd0-1030180f30e4 · outbound

This paper cites Microsoft coco: Common objects in context.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Microsoft coco: Common objects in context

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.672236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125e3ad4-7929-4c1d-86c2-fdfcd50d61e0 · outbound

This paper cites The Llama 3 Herd of Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.677557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b50efe8-27bb-4f7e-ab22-8957671db108 · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.707975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48db200e-9897-465d-b0c7-da738f48eb32 · outbound

This paper cites Gradient-based Jailbreak Images for Multimodal Fusion Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Gradient-based Jailbreak Images for Multimodal Fusion Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.713071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745cbf86-2fd6-47cd-a8a2-7d0b5bb25443 · outbound

This paper cites Intriguing properties of neural networks.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Intriguing properties of neural networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.717986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3930a099-e5d5-404a-9520-7631263bbbaa · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Finetuned Language Models Are Zero-Shot Learners

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.728380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5897041d-e12e-47d8-ab0c-e928252a4a8b · outbound

This paper cites RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.734437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2c60b6-d6f0-4d16-8b8d-8c8fb8bc85f4 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.739329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15272f1c-e302-4d92-8a5b-8337b0449037 · outbound

This paper cites Backtracking Improves Generation Safety.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Backtracking Improves Generation Safety

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.745065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f6a650-6426-4ba0-b89d-53c5743a2b00 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.749549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad0d0f3-61ab-445f-8491-9baacbcb1902 · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Improving Alignment and Robustness with Circuit Breakers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.754273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1caace8-2616-44f7-b1e2-54cad6bb6cc1 · outbound

This paper cites an unresolved cited work.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:41:20.214718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1ffa0eb6-c7c4-4deb-b108-8acbd635c507 · outbound

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

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.617548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e674f15-d8f5-4090-85e4-8fe37aa6ce21 · outbound

This paper cites Large Language Models as Tool Makers.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Large Language Models as Tool Makers

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.631804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f9e599-9525-4fc0-8061-c155fa652406 · outbound

This paper cites Openai o1 system card, 2024.https://cdn.openai.com/o1-system-card-20240917.pdf.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Openai o1 system card, 2024.https://cdn.openai.com/o1-system-card-20240917.pdf

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:41:20.231038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2749a692-ac32-421c-adb6-d5db5bfe6d8c · outbound

This paper cites Introducing v0.5 of the AI Safety Benchmark from MLCommons.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Introducing v0.5 of the AI Safety Benchmark from MLCommons

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.723877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e03006-52c6-478e-905c-a08392c8e9a7 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.647374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e77e521-acc4-49c4-bd51-d2c7bccfff4c · outbound

This paper cites Language Models are Few-Shot Learners.

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations Language Models are Few-Shot Learners

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T19:41:19.623020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5338327d-43fd-40c9-89ac-0a9e9e809fe0 · inbound

Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model cites this paper.

Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T22:06:36.928052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 045b3ac9-2178-4ca6-8ec9-7f65a19bd5e8 · inbound

MSTS: A Multimodal Safety Test Suite for Vision-Language Models cites this paper.

MSTS: A Multimodal Safety Test Suite for Vision-Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T19:27:42.201183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d35bdc-b54e-454b-88a1-c0052816a186 · inbound

Peering Behind the Shield: Guardrail Identification in Large Language Models cites this paper.

Peering Behind the Shield: Guardrail Identification in Large Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-23T03:45:21.411682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2a14a196-5cd8-4644-8dd6-9f5f866d8dca · inbound

Position: Adversarial ML for LLMs Is Not Making Any Progress cites this paper.

Position: Adversarial ML for LLMs Is Not Making Any Progress Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T12:47:21.635346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d1a7cf-e579-4cbb-b1dd-91f41bbf9764 · inbound

Universal Adversarial Attack on Aligned Multimodal LLMs cites this paper.

Universal Adversarial Attack on Aligned Multimodal LLMs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T11:17:01.558974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c9e5cf-e35a-4b7c-abc1-e398f7346f65 · inbound

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning cites this paper.

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-23T01:32:22.636141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c5d15393-8b69-4e68-8c9a-12494ca33dbf · inbound

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation cites this paper.

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T10:57:21.997909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0605da23-8e2d-469d-88f9-c43235685d5f · inbound

Safety in Large Reasoning Models: A Survey cites this paper.

Safety in Large Reasoning Models: A Survey Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T10:36:48.079314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a5519a-a09f-454e-9774-509c90d902ec · inbound

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning cites this paper.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.326452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c328271-341b-45e1-a14a-2386493b51e1 · inbound

CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement cites this paper.

CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:10.476101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44af8039-f98a-4ca2-9be4-5c51c6071f3a · inbound

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs cites this paper.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:21.902482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02ef074-c473-4d5e-9bbc-0e4a8128692e · inbound

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models cites this paper.

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:39.673608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48eb96e2-9bbc-4668-9c72-6313023d7d9b · inbound

Security Concerns for Large Language Models: A Survey cites this paper.

Security Concerns for Large Language Models: A Survey Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:03.421477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f196d9-71c2-43b6-9217-26debf298a97 · inbound

VLMs Can Aggregate Scattered Training Patches cites this paper.

VLMs Can Aggregate Scattered Training Patches Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.820412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9548bc3d-60a6-4042-a178-b1c18432db6a · inbound

Speaking images. A novel framework for the automated self-description of artworks cites this paper.

Speaking images. A novel framework for the automated self-description of artworks Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:51.324825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ec850e-642c-49aa-9266-b79e0230029d · inbound

WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.

WebGuard: Building a Generalizable Guardrail for Web Agents Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T16:12:47.921568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335ee4fe-56fb-4146-923f-8bbbfdab16c3 · inbound

Agentic Web: Weaving the Next Web with AI Agents cites this paper.

Agentic Web: Weaving the Next Web with AI Agents Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T13:05:30.941258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb7fc64-0366-4d19-ab69-4a448b819912 · inbound

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security cites this paper.

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.630560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e27679b-e4c7-415d-9938-5bb015d069a4 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 271

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:08.237034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a441a9e7-6922-4492-8447-1f81cf1845f1 · inbound

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation cites this paper.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.265393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d96b9a3-9a7c-4e5f-ab71-fc09da28f6ae · inbound

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs cites this paper.

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T06:54:13.642986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcab73ec-16b2-4f58-881a-a1cabb3d1221 · inbound

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring cites this paper.

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T22:31:19.456225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9b244e70-b932-4792-b083-a976e5b4c038 · inbound

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models cites this paper.

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T23:16:36.535613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52430498-5737-4640-81de-ad8fcdc47690 · inbound

RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation cites this paper.

RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:28:04.833354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a990da7c-ce50-4c1e-8864-67a0f1e2d993 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.757351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f0a120d-992e-4529-b1ad-1ecd235e2b10 · inbound

Jailbreaking Large Language Models with Morality Attacks cites this paper.

Jailbreaking Large Language Models with Morality Attacks Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:21:27.025753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b829f9bb-64fd-49d5-ac99-66371fee3ea5 · inbound

Human-Guided Harm Recovery for Computer Use Agents cites this paper.

Human-Guided Harm Recovery for Computer Use Agents Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:06:02.872694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6a392a02-df60-413f-a342-aa6f3fbdf70f · inbound

Human-Guided Harm Recovery for Computer Use Agents cites this paper.

Human-Guided Harm Recovery for Computer Use Agents Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-05T10:30:59.156865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation efd652ae-1ba5-4907-97c9-2f8f71ce815d · inbound

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use cites this paper.

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:26:07.011087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e2eb4062-4846-415d-b99b-9e7690c21da3 · inbound

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections cites this paper.

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:45:49.563695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 16f5f3fa-ce5c-4411-a7b3-11bf12a0c391 · inbound

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening cites this paper.

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:08:21.196129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b7f2b4c-9b57-4904-94dd-a40f890aade3 · inbound

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs cites this paper.

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T10:23:12.307541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c42f1064-0c71-4f50-a029-964350980e60 · inbound

Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition cites this paper.

Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:26:23.274369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 143b6443-0812-475e-9e1a-27cdbd5ddecb · inbound

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models cites this paper.

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:56:20.691442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a5cf95bf-4101-4784-a745-27f5f4d0c2ae · inbound

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks cites this paper.

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:47:31.661848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2bc847a2-3b2d-4df4-aa9b-7dc56b2851fd · inbound

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety cites this paper.

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:59:58.594811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ff2f73ca-308d-418c-ae66-c60c96ede16f · inbound

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety cites this paper.

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:03:48.788821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 65a76c93-d42c-4124-aba2-602a70478aa8 · inbound

MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.

MIRAGE: Protecting against Malicious Image Editing via False Moderation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:09:54.627654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 610da550-8323-46f7-8fef-da5744b63825 · inbound

MIRAGE: Protecting against Malicious Image Editing via False Moderation cites this paper.

MIRAGE: Protecting against Malicious Image Editing via False Moderation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:13:53.525339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9345b635-596c-4853-aaa8-959e7a2ecb4c · inbound

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T17:35:51.359552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 28875ef5-b675-4f81-9168-b8f8c73da195 · inbound

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction cites this paper.

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T23:03:12.035774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88504edd-9fff-482e-ba81-12a809bf8798 · inbound

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation cites this paper.

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T07:36:56.205558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11c983ec-144d-4b6a-a90e-7ba8182ad791 · inbound

Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed cites this paper.

Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T09:24:20.410283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27324d3e-51bd-489e-8c99-24bf9002c4bf · inbound

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails cites this paper.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.240423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6d2054-32cc-419f-8e86-cdc0571d642c · inbound

MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration cites this paper.

MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T21:24:14.998324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c98a0a-cdef-483a-947a-b337ca954661 · inbound

Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails cites this paper.

Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T04:34:05.661690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.