Paper Citation Record · LEDGER

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

As of 23 August 2026, this Paper Citation Record lists 100 of 175 outbound references and 16 inbound Pith citation observations for arXiv:2411.09259.

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

pith.paper-citation-record.v1
2411.09259 v2

Coverage vector

measured 100 of 175 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:53:15.043849Z

measured 116 of 116 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:41:29.231103Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T17:20:00.272653Z

Reference resolution

100 of 175 outbound references displayed

verified exact0
verified fuzzy0
unresolved100
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14c1098b-6f05-40de-aaec-06cba19c0958 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.662894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a245001-b204-4e19-ab1a-d4b6e5aacce5 · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Emu3: Next-Token Prediction is All You Need

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.667633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6c8b94-3012-41fc-80b7-f4eacfd0ef19 · outbound

This paper cites Visual instruction tuning,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Visual instruction tuning,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.671558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2625de2c-4825-4b1f-9473-d2cfb793fc65 · outbound

This paper cites Video-llama: An instruction-tuned audio-visual language model for video understanding,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Video-llama: An instruction-tuned audio-visual language model for video understanding,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.675402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac22b32f-518c-489a-9ffa-53932543277a · outbound

This paper cites Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.679185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315ea2fe-55ed-4bf2-a71c-b933fea270d8 · outbound

This paper cites Can i trust your answer? visually grounded video question answering,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Can i trust your answer? visually grounded video question answering,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.683080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b701ffbe-dd39-4e15-9336-49ee0b0ced76 · outbound

This paper cites Fka- owl: Advancing multimodal fake news detection through knowledge- augmented lvlms,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Fka- owl: Advancing multimodal fake news detection through knowledge- augmented lvlms,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.687307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8802ee7a-3fa6-4801-85e0-70a276e6397f · outbound

This paper cites MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.690958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 998ce2e4-c0b3-4561-a00d-fd5a13a725de · outbound

This paper cites Denoising diffusion probabilistic models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Denoising diffusion probabilistic models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.694473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918fb380-ee6e-4d2b-80ca-87c07139a681 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey High- resolution image synthesis with latent diffusion models,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.698053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d08507-86fe-46f7-a015-23f0bc2d126a · outbound

This paper cites Video diffusion models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Video diffusion models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.701161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710bc3b5-1ed9-45e1-92d0-0972cb0c3350 · outbound

This paper cites Instastyle: Inversion noise of a stylized image is secretly a style adviser,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Instastyle: Inversion noise of a stylized image is secretly a style adviser,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.704285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 521ea03d-8132-4da8-adea-16beda8928a6 · outbound

This paper cites Localize, understand, collaborate: Semantic-aware dragging via intention reasoner,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Localize, understand, collaborate: Semantic-aware dragging via intention reasoner,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.707239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550b91d9-00d0-4f80-8158-7e1ecccc3a6e · outbound

This paper cites Amazing “jailbreak.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Amazing “jailbreak

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.710806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77c32ae6-b2ee-46bd-a9fb-5f9c6b707a44 · outbound

This paper cites Jailbreak chat,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreak chat,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.715100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc6821c7-1a4c-47a0-abae-f2cdcc28befc · outbound

This paper cites Multi-step jailbreaking privacy attacks on chatgpt,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Multi-step jailbreaking privacy attacks on chatgpt,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.719137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0b176b-62dc-4846-90fe-b22464ad3047 · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbroken: How does llm safety training fail?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.723000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61e3cfd3-1c64-47f1-8183-273709aa5f5f · outbound

This paper cites Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.726760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f3b3fc-7b86-43c1-ae8e-f60299c2824d · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Mma-diffusion: Multimodal attack on diffusion models,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.730849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64156e39-0e76-451e-b2c4-df8a3ab83808 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey T2vsafetybench: Evaluating the safety of text-to-video generative models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.734527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686d807f-0ad3-41be-aa7d-d676b928655c · outbound

This paper cites Voice Jailbreak Attacks Against GPT-4o.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Voice Jailbreak Attacks Against GPT-4o

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.738270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e990c06c-b75b-4423-a0c9-1f6f8939309d · outbound

This paper cites A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.742190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b6ec95-8122-436d-8fa0-6c826774aaa4 · outbound

This paper cites Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.746425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9597d08a-0378-42b7-9a1e-c25cb9a3f9de · outbound

This paper cites Adversarial attacks and defenses on text-to-image diffusion models: A survey,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Adversarial attacks and defenses on text-to-image diffusion models: A survey,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.750281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8cba1a3-1a8e-4961-beb7-b024a89b9177 · outbound

This paper cites Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.754032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faace1bf-d1e0-461a-91c6-b9b3514daa55 · outbound

This paper cites From llms to mllms: Exploring the landscape of multimodal jailbreaking,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey From llms to mllms: Exploring the landscape of multimodal jailbreaking,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.758775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5b2fc7a-d671-4978-b05e-ffaa1a5964a3 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Minigpt-4: Enhancing vision-language understanding with advanced large language models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.763164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a293fd6-195f-4b51-aa06-c7b4aa10baa0 · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Instructblip: Towards general-purpose vision-language models with instruction tuning,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.767114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c614f829-b71a-48f2-84b6-507e013f53ea · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.771137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574b5f90-f9c7-4ea1-ba9b-7fd229039778 · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.777734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d443b810-d010-47e5-b0bf-bc0df3c5ba2c · outbound

This paper cites Midjourney,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Midjourney,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.782587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e896ef-a8ce-400d-89ab-727866fc43b7 · outbound

This paper cites Moderation overview,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Moderation overview,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.786320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cf2ed0c-7aee-4b97-b001-bd31f93151f4 · outbound

This paper cites Dreambooth: Fine tuning text-to-image diffusion models for subject- driven generation,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Dreambooth: Fine tuning text-to-image diffusion models for subject- driven generation,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.789956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047f9bea-f023-40e1-b7a6-0dd9292c49e7 · outbound

This paper cites InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.793477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8902cacd-9c91-4c47-b339-f836c8b64094 · outbound

This paper cites Open-sora: Democratizing efficient video production for all,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Open-sora: Democratizing efficient video production for all,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.797261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc5de44-5a52-4d42-92f1-7ab9ecf08cf9 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.800657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c7e3cab-0274-4f44-ac84-2b4cd0e90dda · outbound

This paper cites Videopoet: A large language model for zero-shot video generation,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Videopoet: A large language model for zero-shot video generation,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.804747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b744db21-7616-4b0f-8215-3bc34e6bce1f · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.807957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 915551a2-5f07-426a-ba14-34b835c0b8cb · outbound

This paper cites Next-gpt: Any-to-any multimodal llm,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Next-gpt: Any-to-any multimodal llm,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.811532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e1cce58-d255-4c6a-8797-7d02298dc57f · outbound

This paper cites Chameleon: Plug-and-play compositional reasoning with large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Chameleon: Plug-and-play compositional reasoning with large language models,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.814765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc19d8b-fe41-48c0-88b6-d690dae634d0 · outbound

This paper cites GPT-4o System Card,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey GPT-4o System Card,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.818343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33dd1e47-cb3d-4945-a944-3566795c961d · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Learning transferable visual models from natural language supervision,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.821895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 307d0b53-8eb5-4142-bf70-1922fa38d920 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.825511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e00f0501-0248-4f15-9355-b6693121ec86 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Gemini: A Family of Highly Capable Multimodal Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.829094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3b5c795-8ee7-4fc7-86f9-a94f731c9f64 · outbound

This paper cites Diffusion Model-Based Image Editing: A Survey.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Diffusion Model-Based Image Editing: A Survey

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.832740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff48d5ba-0ff4-4b35-9ae6-f1f7dda71d29 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Classifier-Free Diffusion Guidance

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.837366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d76793b-6337-41dd-ae74-3d3793ceb15a · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.841318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14ed539-dc3e-4c88-88c4-53a03a97039b · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.845111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd4e6aa-3136-40aa-b77b-02a00f260bc0 · outbound

This paper cites Cognitive overload: Jailbreaking large language models with overloaded logical thinking,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Cognitive overload: Jailbreaking large language models with overloaded logical thinking,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.848885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d68618b-11f1-47a9-9998-61c5ca9bd6ff · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 19 AI safety by humanizing llms,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 19 AI safety by humanizing llms,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.852245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 394a944e-ba19-4974-a59d-046893e257b4 · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Autodan: Generating stealthy jailbreak prompts on aligned large language models,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.856238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8bfbeb-4b2c-4871-995a-6c41e79efe58 · outbound

This paper cites BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.859599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278c3159-6917-4117-b821-0851c991941d · outbound

This paper cites Ring-a-bell! how reliable are concept removal methods for diffusion models?.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Ring-a-bell! how reliable are concept removal methods for diffusion models?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.863350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae715504-4cec-458d-9c42-e44bb0f75f92 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.867437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc66d4b8-edfb-4919-85b2-0289be679eab · outbound

This paper cites Mm-safetybench: A benchmark for safety evaluation of multimodal large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Mm-safetybench: A benchmark for safety evaluation of multimodal large language models,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.871426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a4f37c1-2bf1-4e9e-b3b3-59a853fe227f · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Gradient-based Jailbreak Images for Multimodal Fusion Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.874876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0b6a74f-3c12-4258-a542-bd4a8a5f4727 · outbound

This paper cites Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.878526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15066ac7-7baf-4e59-a5e7-67d913c63df3 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.882071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e9e44e2-5d85-4e79-842a-72b54eaf1938 · outbound

This paper cites Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.885584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b82d7bb9-e9ed-4196-84d6-5832aa0c70d5 · outbound

This paper cites Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.889744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1f8f83-084b-4be3-b018-9754a4142283 · outbound

This paper cites Safe-clip: Removing nsfw concepts from vision-and-language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Safe-clip: Removing nsfw concepts from vision-and-language models,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.893818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85723840-7d94-4da0-947c-1b5035870150 · outbound

This paper cites Can large language models automatically jailbreak gpt-4v?.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Can large language models automatically jailbreak gpt-4v?

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.897070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31b6a564-34d8-45e0-ac88-9a991e8a63e8 · outbound

This paper cites Arondight: Red teaming large vision language models with auto-generated multi-modal jailbreak prompts,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Arondight: Red teaming large vision language models with auto-generated multi-modal jailbreak prompts,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.901093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0945ce6-f0f6-4775-9887-602df82b7143 · outbound

This paper cites AdvAgent: Controllable Blackbox Red-teaming on Web Agents.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.904442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b0ab78-14e4-4b1f-bb51-53c187f2c7dc · outbound

This paper cites Red-teaming the stable diffusion safety filter,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Red-teaming the stable diffusion safety filter,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.907665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c52f414e-406b-41fb-955b-f74f1c64bdcd · outbound

This paper cites Perception-guided Jailbreak against Text-to-Image Models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Perception-guided Jailbreak against Text-to-Image Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.910789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53ead6a-a330-4480-b45e-2204232da748 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Surrogateprompt: Bypassing the safety filter of text-to-image models via substitution,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.914433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae63fc3a-627a-4b9f-99d7-7dbbb5dc8ae1 · outbound

This paper cites Coljailbreak: Col- laborative generation and editing for jailbreaking text-to-image deep generation,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Coljailbreak: Col- laborative generation and editing for jailbreaking text-to-image deep generation,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.917468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e12bfb04-e5d0-4bc7-a70b-1b58b7c6bbab · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Harnessing LLM to Attack LLM-Guarded Text-to-Image Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.920581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67906f85-a815-45aa-87db-6a4436e882fe · outbound

This paper cites Upam: Unified prompt attack in text-to- image generation models against both textual filters and visual checkers,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Upam: Unified prompt attack in text-to- image generation models against both textual filters and visual checkers,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.924136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

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 b4850035-b51a-4098-af0b-ace4501f4286 · outbound

This paper cites Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.931879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f23ffd3-82e0-4ae1-a2ff-a6a6a0ea3742 · outbound

This paper cites Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.936399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5307a00a-5938-4cbf-9f3f-646a64cd9d10 · outbound

This paper cites Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.940230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71697d35-92aa-4a00-8c36-2422f149c815 · outbound

This paper cites Zer0-jack: A memory-efficient gradient- based jailbreaking method for black-box multi-modal large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Zer0-jack: A memory-efficient gradient- based jailbreaking method for black-box multi-modal large language models,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.943985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cfccdbd-d942-405e-8219-ce41e5a2dad9 · outbound

This paper cites DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.947833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a94ef49c-8b09-434e-91d8-8b0bb1269e69 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Sneakyprompt: Jailbreaking text-to-image generative models,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.951472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8047497f-6431-4694-a099-614c5e31aaef · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.954938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c0ec777-4f6f-47e9-a40d-68cef90d35ca · outbound

This paper cites Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.958989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da43780d-4c4b-40d3-b49b-9decc3f873f5 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.962860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e584d4a-39e2-48de-b825-313e3470a1af · outbound

This paper cites Ideator: Jailbreaking vlms using vlms,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Ideator: Jailbreaking vlms using vlms,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.967167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 597e3242-ad5b-4245-b6c9-b63fc8604af8 · outbound

This paper cites Automatic Jailbreaking of the Text-to-Image Generative AI Systems.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Automatic Jailbreaking of the Text-to-Image Generative AI Systems

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.970948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9046b0f-a336-4d8f-850d-75c2b79d8882 · outbound

This paper cites Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.974755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d4b3503-528e-49fa-a0a6-0b2bd5d7ae4c · outbound

This paper cites Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.978819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92db9804-dce3-4c5b-a14c-b685805781d7 · outbound

This paper cites Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.982659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8999d5cf-0913-469d-8784-3f67baebf952 · outbound

This paper cites How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.986559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9a234b3-c97f-441a-987e-e74c0ecf33ec · outbound

This paper cites Image hijacks: Adversarial images can control generative models at runtime,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Image hijacks: Adversarial images can control generative models at runtime,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.990170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081bf895-a0e0-4b9d-838f-7ca4eea09ddd · outbound

This paper cites Visual adversarial examples jailbreak aligned large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Visual adversarial examples jailbreak aligned large language models,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.993183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acef5543-119d-482e-a66c-0ffd9a007ad6 · outbound

This paper cites Efficient llm-jailbreaking by introducing visual modality,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Efficient llm-jailbreaking by introducing visual modality,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:14.996148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ab7b6f-f07b-4332-a4e9-e2fa44e1d94d · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreaking Attack against Multimodal Large Language Model

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.000463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3d6348c-2436-4289-ac6e-3f7ea2b327b2 · outbound

This paper cites Are aligned neural networks adversarially aligned?.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Are aligned neural networks adversarially aligned?

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.005060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3b4adc5-09bb-4fff-940a-740b3cd50b6c · outbound

This paper cites Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.009206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45498c45-6ec8-4ae7-8f09-6769feef39c2 · outbound

This paper cites Agent smith: A single image can jailbreak one million multimodal llm agents exponentially fast,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Agent smith: A single image can jailbreak one million multimodal llm agents exponentially fast,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.014192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74037105-aa2e-4c11-a159-6d640bd0eafd · outbound

This paper cites White- box multimodal jailbreaks against large vision-language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey White- box multimodal jailbreaks against large vision-language models,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.019021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4619acca-29f7-42f3-8aa5-bb477dad491e · outbound

This paper cites Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.023557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2076245-8e93-45de-9b70-c2222c32f9fd · outbound

This paper cites Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts,

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.027882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a593f76-4e0c-45c9-a26f-36a0adc15057 · outbound

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

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images... for now,

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.031741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db93e961-62ed-42e7-ae35-0f13911cf7a7 · outbound

This paper cites Va3: Virtually assured amplification attack on probabilistic copyright protection for text-to-image generative models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey Va3: Virtually assured amplification attack on probabilistic copyright protection for text-to-image generative models,

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.036119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 338af660-7466-4725-89b9-3f70231f601d · outbound

This paper cites On evaluating adversarial robustness of large vision-language models,.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey On evaluating adversarial robustness of large vision-language models,

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.039732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f09930-d9d0-40fa-855a-024dd9a0068a · outbound

This paper cites AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models.

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-12T20:53:15.043849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8c5e5d15-26a8-41bf-ab98-b685393a9d97 · 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 Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T21:45:34.754730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb6336ee-e3cc-4656-a4ba-15764670ad3f · 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 Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:57.409109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa1d2957-556e-42e4-843f-05f67e725e3e · inbound

Survey on AI-Generated Media Detection: From Non-MLLM to MLLM cites this paper.

Survey on AI-Generated Media Detection: From Non-MLLM to MLLM Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T21:12:22.382439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27124562-0815-40c5-a592-257b84ea0a07 · 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 Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:18.501499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93349ea9-04f3-46e8-a6d3-80815e5bbbfc · inbound

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models cites this paper.

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:29.231103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22cd4118-cbb3-4f54-9993-a9cb10e74468 · 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 Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:35.615647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b995f9b-280f-4712-aec3-df69f68af75e · inbound

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models cites this paper.

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T04:08:48.559350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6bd18e-0eb4-41d3-b017-c8588d4958b1 · 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 Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.678523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d7d340-2893-4e82-9905-965fbde5a342 · inbound

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention cites this paper.

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:21.309150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0b78cb-4f63-44f2-bcbf-5a7b8fd736bb · inbound

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding cites this paper.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.242527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da70b34-d1ac-45e5-bd14-ea2616f1901a · inbound

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization cites this paper.

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:58.994123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fa298c4f-227e-49dc-9ece-b73101bfe4ac · inbound

Latent Space Probing for Adult Content Detection in Video Generative Models cites this paper.

Latent Space Probing for Adult Content Detection in Video Generative Models Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:46:11.927058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7af958cb-f4df-4a1c-8921-dc2ff70991ad · inbound

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction cites this paper.

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:58:13.607221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6d081d0f-b038-4092-9de6-b8b2926b3543 · inbound

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation cites this paper.

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:20:00.274254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a4b7d2bc-1709-4d4c-a6fd-1c95fbc5f6b3 · inbound

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure cites this paper.

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T08:23:25.193531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d16fb8a1-8f47-4dc4-88cc-5555cb0c6efd · inbound

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks cites this paper.

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T13:07:51.818433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.