Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T15:06:43.140580Z
Paper Citation Record · LEDGER
As of 3 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 1 inbound Pith citation observation for arXiv:2604.12616.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T15:06:43.140580Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T02:44:13.644542Z
A source-named dated measurement, never combined with another source.
Source: cited_works
63 of 63 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation d9fc1dd2-a021-4347-ba30-6b9a704aa26d · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 0417bc13-3a5f-49d6-9929-c07f9d15aec8 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3f804cb1-ce7c-414f-99f6-24d65acefc11 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , year =
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 6322f05b-9528-4d03-a836-a22fd748ee24 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 22702ab2-e43c-4599-bc3e-d96b2b602d23 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 86133c2f-bdc7-43ce-8f57-fa6e2d89ecbf · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 385ef909-07e9-4842-b8a9-50f2d593d6c1 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ee2f2bb6-2f70-46f2-acb6-0075cde24b6d · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 2fbfbdb7-3bf4-4da1-9342-5934c18c20ff · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation c6348f86-cafe-4cd9-9d37-8af063015e45 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Qwen3-VL Technical Report
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation e0900156-f996-4636-b475-b5bdc32e9b9c · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 9baf8ce6-e296-48d0-9078-4b3900b9261c · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation eac0e59c-228f-4e21-abf1-8fdfe685d1b1 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Tree-based dialogue reinforced policy optimization for red-teaming attacks
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 33231b45-32de-4982-8e26-6d79e350a989 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation e5d807d1-8bf1-489e-8f1e-0785aca47fd6 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 98cbaeb7-5cfd-41a3-b9a4-7c001bc5dc6f · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 993483cd-befb-4489-b115-789523ec2f63 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ed3b49ce-82c1-480d-a71f-4e369f40361b · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 207b53f4-7f38-4914-8dfa-86118fc878cf · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3b14ce19-a91c-488d-aefd-838dec9c6758 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 6f7dac83-8c85-49e1-9fa7-c61a78ea7039 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Lawrence Zitnick
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation caa7e3ad-c817-49dc-ac0c-e10fbdb1009b · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Improved Baselines with Visual Instruction Tuning
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 69cd6318-8040-4648-aa31-5da6a783bd4f · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3d294c83-fe80-44f9-a00a-c72a1cd9c73d · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 24
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ee0ff9d1-3e8c-4ce3-a64b-9a31ea9420a1 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation e79cba21-01f1-4557-b032-b0dda5d71dcd · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5d35ea30-6ea0-438b-848c-7c2399bc7671 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ca267615-9cb7-418f-8dee-d30f043a325c · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation bd104802-2d95-4646-9556-eb8b155fc22c · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1cb5aea9-9360-4888-ab71-93933af2fed7 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 02e0652a-f8f8-45c8-8671-15c73833a8c9 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Advances in Neural Information Processing Systems , volume =
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 75049536-ebbe-4c1e-a2a6-12e80a9ab438 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 196a48cc-5a81-485c-9833-f95b313cdbac · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation f6727b7a-bc53-41e2-ac0f-10da53980a4e · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Jailbreaking Attack against Multimodal Large Language Model
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 15064cfd-c91d-46a9-9bed-2246a1dea3af · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 6cb2bc32-ee57-4175-b821-7ceedacdaf32 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , year =
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation fcac2ebc-428f-4de1-87f5-62da0b4e464e · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs In: Wooldridge, M.J., Dy, J.G., Natarajan, S
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation fa016be3-4ba5-46e9-afb5-eb87272e954a · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 45bf207a-4f02-407e-87b0-5791b19c1a0f · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation cc6911e2-b2d2-47ad-896f-9bb84ea34336 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 257459ce-a4f2-4657-aef1-1d72628f4542 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Graph of attacks with pruning: Optimizing stealthy jailbreak prompt generation for enhanced llm content moderation
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 2f1daa98-92c9-4d39-92c6-587cba99b950 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Alphasteer: Learn- ing refusal steering with principled null-space constraint
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1b8c2cb7-810d-421d-8edd-42cd11a42593 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation da6b19da-2b98-47c7-a9ca-a36550563b6f · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 95d76b98-1055-4ea3-9d45-bff5e1e27199 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ac155ce7-2c5b-4378-80c5-af1e36364540 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Kimi K2.5: Visual Agentic Intelligence
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 6c728998-3b2d-42e9-9500-5b663e24e0d7 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Qwen3 Technical Report
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 0400511a-8c66-4178-8e4d-f5134b8ad98e · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation c49b15cc-542d-4760-bb08-87db5913faae · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Voyager: An Open-Ended Embodied Agent with Large Language Models
Reference 49
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 21fd1ce9-24ff-44f1-a803-7f979c359d75 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 50
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5ae38cc5-e964-4cae-9244-bf7870fe0538 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 51
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 4b8c64a4-72cc-4163-a3ea-5fcd5a327d41 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Jailbreak large vision-language models through multi-modal linkage
Reference 52
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation fa7e3ed3-0462-4e1c-ace5-56ac4f9ed408 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 53
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 4fcebdfc-ab05-4d9a-aa17-7b06a7555fc7 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 54
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1e0820fd-23f2-43da-b1bb-fdece08d6bd6 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs doi:10.18653/v1/2025.findings-acl.745
Reference 55
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 2c8098e4-cca3-4251-bcbf-635e660be0ad · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 56
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1d61a655-41af-436f-99a8-5929f10ca057 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Freeman, Frédo Durand, Eli Shechtman, and Xun Huang
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 18a0f2e9-5296-4341-928c-b76789fe7282 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Jailbreak vision language models via bi-modal adversarial prompt.IEEE Transactions on Information Forensics and Security, 20:7153–7165, 2025
Reference 58
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 11f15b1e-bf2d-455c-94b2-bcfea0711a23 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Freeman, Frédo Durand, Eli Shechtman, and Xun Huang
Reference 59
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 9907746f-35e6-4bc4-9247-2c87138b28bf · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Qwen3Guard Technical Report
Reference 60
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 92d96a0d-5e38-4197-863b-238b806111ec · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 61
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 087f8f43-3d0c-45bd-806c-a3acf0ff1aac · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Unresolved cited work
Reference 62
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 49b13a73-32e6-4f88-8d31-a8249e34a368 · outbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 63
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation d430814e-b2b2-4e82-9c3d-bf34a6ec2e5f · inbound
Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.