FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts | Paper Citation Record

Observation d6611326-d04b-4e0e-a9eb-3c0a32f7beac · inbound

Jailbreak Attacks and Defenses Against Large Language Models: A Survey cites this paper.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:20:44.644037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 20571498-ca2c-4d01-b1ad-cf4779b735d0 · inbound

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions cites this paper.

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 261

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:55:49.827489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f590a976-a726-4e93-a67b-bcf63b63f027 · inbound

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense cites this paper.

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T21:45:34.681816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0f850f-fcfb-4952-911f-9cfe9e31dfe5 · inbound

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey cites this paper.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.927923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1073da5-1b48-4e04-98fd-b3114cc1f269 · inbound

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents cites this paper.

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-12T20:36:01.688800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f66642a-eb7d-443e-a0ea-ed7e5c5cbd49 · inbound

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models cites this paper.

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T18:32:12.008410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455e54ab-a27b-4814-8c6b-0ccdb3868698 · inbound

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks cites this paper.

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T14:04:45.364618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acfaf43-7260-48f6-a294-f1aa1ffd933a · inbound

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks cites this paper.

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T14:24:32.422535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1bc228-aa78-4677-8435-e35e65ea3596 · inbound

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment cites this paper.

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T11:03:01.068838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d59096-0e05-46ee-bf34-88367218808a · inbound

VLSBench: Unveiling Visual Leakage in Multimodal Safety cites this paper.

VLSBench: Unveiling Visual Leakage in Multimodal Safety FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T05:56:46.382144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1623d3-0fbe-4081-81a6-db20054458ab · inbound

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds cites this paper.

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:53:37.051669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a10f859c-81cf-4f5d-bcbb-ef1ca7fee064 · inbound

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models cites this paper.

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:17:02.618814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b1736b7-ac9a-4c0e-8d82-b797a7d691ff · inbound

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision cites this paper.

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T13:52:06.451631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2b8983-526d-4d18-8a3a-aeecf1f3d099 · inbound

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models cites this paper.

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T10:32:28.253863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c6a18c-c7e6-4fe6-9688-fc3c4da0504d · inbound

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting cites this paper.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.239283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f0defe-be02-4549-bfa7-49a3947901f2 · inbound

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models cites this paper.

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T22:28:32.275326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6af22920-5d93-4986-82a1-db96bc17f2c1 · inbound

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering cites this paper.

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T22:03:25.182762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58de6437-1fcc-45b6-b975-e6141587a160 · inbound

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency cites this paper.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.521572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68faee73-b6c2-4a4d-be86-451e438c806a · inbound

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness cites this paper.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.539812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff11f3ff-3dff-4ef0-93c9-6c0e284c5670 · inbound

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

MSTS: A Multimodal Safety Test Suite for Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:27:42.222300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8daa2fc-b5c4-433c-9815-f0bc5301c395 · inbound

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink cites this paper.

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T14:29:27.955780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5ddc72-7959-432a-9303-81335cb62a47 · inbound

Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update cites this paper.

Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T15:19:10.058952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9286d120-4a50-4efb-b285-aeaf00e32d60 · inbound

Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation cites this paper.

Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T18:31:14.087069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06db8f48-9059-46fa-bec0-a95bce650ee8 · inbound

`Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs cites this paper.

`Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:57.502267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dcd471c-92c4-46e6-8864-473a96d2d4d7 · inbound

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

Peering Behind the Shield: Guardrail Identification in Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-23T03:45:21.421463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 45db22fc-32bf-4669-aa6e-79235529bc6e · inbound

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models cites this paper.

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T14:58:53.648957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3a88df-54f0-4c89-9c74-a5b3a3237360 · inbound

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs cites this paper.

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T15:38:17.245674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a28ffb6-f22f-4ade-aba3-4914e6ba9bfe · inbound

Universal Adversarial Attack on Aligned Multimodal LLMs cites this paper.

Universal Adversarial Attack on Aligned Multimodal LLMs FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T11:17:01.577794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b4a0320-2e8a-4784-bf05-44489b5580c7 · inbound

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations cites this paper.

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:18.513844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a447fef4-d575-4fbf-b5c6-439c13bc93bd · inbound

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion cites this paper.

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-23T00:15:14.901879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0f36ae66-b552-4414-be16-ba32471dcfee · inbound

Manipulating Multimodal Agents via Cross-Modal Prompt Injection cites this paper.

Manipulating Multimodal Agents via Cross-Modal Prompt Injection FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T11:55:40.174005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ecdc404-efe4-4b23-ba54-eefb57098d32 · inbound

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models cites this paper.

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:59.043297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d9547d3-307b-4888-9c84-c4832b70f0ad · inbound

REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM cites this paper.

REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T23:36:00.995456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48419eff-b2b3-43aa-8648-18699d8d518f · inbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.372492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103793a0-decc-44e8-bd1a-2f4d876afd11 · inbound

Backdoor Cleaning without External Guidance in MLLM Fine-tuning cites this paper.

Backdoor Cleaning without External Guidance in MLLM Fine-tuning FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:50.049188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8124b6-20c0-41e0-a7c7-ed3b7ee9bce7 · inbound

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework cites this paper.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.699522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ff5cd9d-7983-411d-a328-87439cb68029 · inbound

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration cites this paper.

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:11.421412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 154a0da8-bb06-4901-b630-d98a7539b344 · inbound

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack cites this paper.

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:00.808067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9a16fcf-f021-4a0c-a6cb-addc007f4cbc · inbound

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models cites this paper.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.261903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197b9f6a-0da3-4cf5-a240-b7adcd798e32 · inbound

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models cites this paper.

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:34:37.104583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15745a6e-fa80-4aa0-b09a-8879aa8366e6 · inbound

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders cites this paper.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.878499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dacb2f80-318f-4ac3-bbe4-bcd682011472 · inbound

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities cites this paper.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.166840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21cc80ab-5b0e-443a-801f-4c1316b01b37 · inbound

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem cites this paper.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.795414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b78950-31ea-4ae7-a11a-c446900e07a2 · inbound

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message cites this paper.

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:46:25.203611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 646bbd30-5388-4171-9b02-5d93ffeb2371 · inbound

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World cites this paper.

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:46:11.544437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d549b25a-4dac-4f19-9750-9debf0272fd8 · inbound

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities cites this paper.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.208807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f27bd73-024c-4e13-adfe-8123bb08ea74 · inbound

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models cites this paper.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:40:05.291273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebab30ad-0dee-4a65-835b-e9d800498ce6 · 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 FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:39.668500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d510cf0d-ca3a-4b04-b357-685170176142 · inbound

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair cites this paper.

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T22:21:02.779195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d54ccb-3003-4fc0-aa8a-ac732c816833 · inbound

Blockchain Network Analysis using Quantum Inspired Graph Neural Networks & Ensemble Models cites this paper.

Blockchain Network Analysis using Quantum Inspired Graph Neural Networks & Ensemble Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T21:22:36.936309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5740cbd4-b93f-4ade-b1a0-87b323e0e519 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:43.152848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4b7143d-a5e2-4c76-abb8-656d7930f615 · inbound

Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models cites this paper.

Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T13:44:55.849334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c40d6e0-a570-4127-b746-4696d7e71c9f · inbound

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs cites this paper.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.482899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 065152dd-2878-42c2-ae83-a853d098f144 · inbound

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models cites this paper.

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T01:22:20.345146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c782b4e9-3165-442d-a618-76714429a737 · inbound

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training cites this paper.

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:45:50.717999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 33eee8d1-b51e-4d1d-ac56-a4ab45110693 · inbound

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations cites this paper.

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:21:15.062154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c4d9e311-7b61-4e74-90e8-cf1d6cfc511a · inbound

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models cites this paper.

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:56:08.044730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1a793493-6053-4015-b0b5-66b60f0b1867 · inbound

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing cites this paper.

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T05:51:27.613031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52479ce2-430d-4a5a-9cd6-745d42dcee2e · inbound

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges cites this paper.

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:27:31.023210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cce14d1e-e0ed-4e91-be22-99cc7cca0d5a · inbound

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models cites this paper.

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-26T04:38:59.203237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bfae213e-9029-4b58-954f-127a92ef4fd2 · inbound

Securing Multimodal AI through Internal Information Decomposition cites this paper.

Securing Multimodal AI through Internal Information Decomposition FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.139372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3a5ca68-e5e4-475a-9d0b-7ca49e3997bb · inbound

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination cites this paper.

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.682360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef8609ee-5f43-433f-80a7-e685488daf32 · inbound

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use cites this paper.

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T04:40:32.663900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28abac41-ddee-48b4-b94f-af4761b95fc6 · inbound

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning cites this paper.

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T14:24:49.599621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers