Paper Citation Record · LEDGER

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

As of 20 August 2026, this Paper Citation Record lists 100 of 156 outbound references and 6 inbound Pith citation observations for arXiv:2506.15170.

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

pith.paper-citation-record.v1
2506.15170 v3

Coverage vector

measured 100 of 156 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:45:09.951094Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:28:46.534696Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T10:04:58.934859Z

Reference resolution

100 of 156 outbound references displayed

verified exact1
verified fuzzy0
unresolved99
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 27724d27-abf5-4e7c-a4a3-f15939c9f3cf · outbound

This paper cites Learning internal representations by error propagation,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Learning internal representations by error propagation,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.444667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81953198-f349-4424-a848-c038b30fdcbe · outbound

This paper cites Long short-term memory,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Long short-term memory,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.450284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb180bd0-54ca-47a7-a298-e33def43b67b · outbound

This paper cites On the difficulty of training recurrent neural networks,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem On the difficulty of training recurrent neural networks,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.455503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fc30e1-cab6-406e-ad38-eca5d2147489 · outbound

This paper cites Attention is all you need,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Attention is all you need,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.460504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5eaf477-c0f5-4533-8605-0cfb1355948a · outbound

This paper cites Deep residual learning for image recognition,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Deep residual learning for image recognition,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.465390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c93b7c78-781e-4c79-babf-d78f38b6eae1 · outbound

This paper cites Layer Normalization.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Layer Normalization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.470329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c10b99-142c-487b-bfd2-4cdc94dc7783 · outbound

This paper cites Scaling Laws for Neural Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Scaling Laws for Neural Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.476310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5335673-89fd-418a-844c-b3d4df2a3d13 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.481358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1fd26d-8601-403a-bef2-03fb69002d40 · outbound

This paper cites Language models are few-shot learners,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Language models are few-shot learners,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.485984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23afcdc2-cced-447d-b19b-634db4126468 · outbound

This paper cites Palm: Scaling language modeling with pathways,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Palm: Scaling language modeling with pathways,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.490727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce774d9-fc6a-46ed-8e62-70c2faf43943 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Learning transferable visual models from natural language supervision,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.495345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b70629-c3ee-4dc6-aa09-1e4f7c54782d · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.501215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f44a029b-0471-4fa3-bae5-2cf7e832aebe · outbound

This paper cites Training language models to follow instructions with human feedback,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Training language models to follow instructions with human feedback,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.506553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18b08c3-8e2b-4eb2-8f70-914b8a5bfc60 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Lora: Low-rank adaptation of large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.511535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c959351f-2771-480b-8f21-e36af4359a5f · outbound

This paper cites GPT-4 Technical Report.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem GPT-4 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.516676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 954ccdea-4315-49d2-b8b0-130972199a79 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.522103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea0d589-d591-432d-ae04-38c43fa9c21d · outbound

This paper cites Adaptive mixtures of local experts,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Adaptive mixtures of local experts,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.527072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 049a54a6-2e5c-4b88-90c2-0bc85419144a · outbound

This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.531960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4c1e62-3038-45bc-bd3f-3530099e4ccd · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem From llms to mllms: Exploring the landscape of multimodal jailbreaking,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.536991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5af09ae-f936-4972-b5d1-2e8e9c32b23c · outbound

This paper cites The rise and potential of large language model based agents: A survey,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem The rise and potential of large language model based agents: A survey,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.542053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0efccd7f-7016-47e1-ba51-c6322c2fa4ab · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.547472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c62f1c0-4d6d-4cd9-8db8-d688b144b994 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Visual adversarial examples jailbreak aligned large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.552294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e537e810-c83c-4464-9af4-b3ff3c9a352b · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.557767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e14267-9edb-4393-acd3-b185c0e9545a · outbound

This paper cites Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.562953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89392231-2862-42bb-a3bd-c7f147d01d95 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.568201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4939d50-c51a-4ce3-afb2-d89ea056c1ff · outbound

This paper cites A wolf in sheep’s clothing: General- ized nested jailbreak prompts can fool large language models easily,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem A wolf in sheep’s clothing: General- ized nested jailbreak prompts can fool large language models easily,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.573266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9035d1c3-c7e9-4667-9a25-fca322d3a1f4 · outbound

This paper cites Making them ask and answer: Jailbreaking large language models in few queries via disguise and reconstruction,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Making them ask and answer: Jailbreaking large language models in few queries via disguise and reconstruction,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.578107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f17635-7aac-4e5a-9dd8-01c01ce829e5 · outbound

This paper cites ” do anything now.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem ” do anything now

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.582743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 634afde2-cf65-4c9b-ae1f-06c2bd8ede02 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Autodan: Generating stealthy jailbreak prompts on aligned large language models,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.587324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd7ff32e-0ced-4313-97a9-1f17b7752c53 · outbound

This paper cites Don’t listen to me: understanding and exploring jailbreak prompts of large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Don’t listen to me: understanding and exploring jailbreak prompts of large language models,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.591981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3480e90f-be71-4501-8f85-c06324154c34 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.597001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86cc3bfa-c9d6-44f2-980b-f6c0ea60aaa1 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem On evaluating adversarial robustness of large vision-language models,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.602221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be9c1977-4ea1-4bb0-8972-3382a573fc5a · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.607298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b082b79-34ad-417c-b263-2d4f54e89635 · outbound

This paper cites Imgtrojan: Jailbreaking vision-language models with one image,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Imgtrojan: Jailbreaking vision-language models with one image,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.612881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b579cc2-82e4-4591-86cf-67d53f41e790 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Image hijacks: Adversarial images can control generative models at runtime,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.617674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33da4556-2d04-498d-8521-cd67e39cf807 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Voice Jailbreak Attacks Against GPT-4o

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.622337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e89faf9-7e7f-4500-863e-754565c558cc · outbound

This paper cites Are You Human? An Adversarial Benchmark to Expose LLMs.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Are You Human? An Adversarial Benchmark to Expose LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.627281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c909433-63e4-4e9c-9340-d03f82032a7e · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.632132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6d556a-3bbb-4f91-a446-7947bb75b524 · outbound

This paper cites Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.637434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d24ef84a-694e-4e49-93ce-6d2067131dcb · outbound

This paper cites Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.642395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93a5bcd0-48c1-446b-bc21-f30a548adbc8 · outbound

This paper cites Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.647198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcaebf48-06f4-4177-a7e7-762977a5999f · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.652323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f14a72-411c-41bb-958a-4da9f74cdbab · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.657625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84a1e4fa-6c94-461d-9891-f2c4c606835a · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.663445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4750ce5e-5bcb-4305-9113-8bb7803f2586 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.668648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd1a03ca-c710-4972-926b-938f4d9a33af · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbroken: How does llm safety training fail?

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.673451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6bd18e-0eb4-41d3-b017-c8588d4958b1 · outbound

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

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 501e6082-77a2-4690-bb4c-ea4a317d3ac2 · outbound

This paper cites From chatgpt to threatgpt: Impact of generative ai in cybersecurity and privacy,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem From chatgpt to threatgpt: Impact of generative ai in cybersecurity and privacy,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.683544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de5efda4-f662-4579-b2f7-ab8818df9e95 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.688519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d86aa15-c8d8-4beb-ba25-e06c5531933f · outbound

This paper cites Exploiting large language models (llms) through deception techniques and persuasion principles,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Exploiting large language models (llms) through deception techniques and persuasion principles,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.693761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f9fa47d-b57a-4350-adc1-a40550363fea · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.698989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006d8d50-e0d6-49ff-9a5d-9cf1804734c2 · outbound

This paper cites Tricking llms into disobedience: Formalizing, analyzing, and detecting jailbreaks,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Tricking llms into disobedience: Formalizing, analyzing, and detecting jailbreaks,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.703695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56cab16d-aec3-4eb1-ac41-4b75134063a6 · outbound

This paper cites Coercing llms to do and reveal (almost) anything,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Coercing llms to do and reveal (almost) anything,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.708719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b083163d-a962-409e-9f8a-ead730dba219 · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.713699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c90bca7-fb16-4ae6-8b23-5dadd980e2c1 · outbound

This paper cites Improving language understanding by generative pre-training,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Improving language understanding by generative pre-training,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.719082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0945efc-d490-439d-9aa4-e7cc95229342 · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Flamingo: a visual language model for few-shot learning,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.723731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550b7808-2a9b-49fd-86b4-0096f4bf1af5 · outbound

This paper cites The art of defending: A systematic evaluation and analysis of llm defense strategies on safety and over-defensiveness,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem The art of defending: A systematic evaluation and analysis of llm defense strategies on safety and over-defensiveness,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.728238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46ea31f1-029f-491c-bd72-6165efda4af8 · outbound

This paper cites Revisiting jailbreaking for large language models: A representation engineering perspective,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Revisiting jailbreaking for large language models: A representation engineering perspective,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.733158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0567a954-a616-4041-928c-c76e96c8693c · outbound

This paper cites Align is not enough: Multimodal universal jailbreak attack against multimodal large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Align is not enough: Multimodal universal jailbreak attack against multimodal large language models,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.737753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c70de8-d251-4d3a-b0c1-a75d6e311098 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreaking Attack against Multimodal Large Language Model

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.742493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed124a4-2e01-4b4a-bebd-c3f258ebbf15 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.747284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71b864ae-48b8-45d0-87a3-28dfff1d2c0c · outbound

This paper cites JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.751937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75786dc7-c6d6-4ff3-8d31-f3d1182b3e63 · outbound

This paper cites Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.757255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce062146-d95f-49be-bbcd-428f347208e8 · outbound

This paper cites Jbfuzz: Jailbreaking llms efficiently and effectively using fuzzing,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jbfuzz: Jailbreaking llms efficiently and effectively using fuzzing,

Reference 64

Resolution: verified exact; raw_fallback, observed 2026-08-15T19:45:11.406419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ac2c8269-16fc-4799-b7ba-82a192827e48 · outbound

This paper cites Jailbreak Large Vision-Language Models Through Multi-Modal Linkage.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.767351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41085b23-2488-4f44-b2f7-9983bccfd410 · outbound

This paper cites Harmful helper: Perform malicious tasks? web ai agents might help,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Harmful helper: Perform malicious tasks? web ai agents might help,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.773007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691dc8ac-c4df-4f94-949c-8c447238318f · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem White-box multimodal jailbreaks against large vision-language models,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.779551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9304d22b-59eb-4198-b1aa-b88d998fdf80 · outbound

This paper cites An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.785180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4838eb26-a3d9-498e-aee6-eed632f3dc06 · outbound

This paper cites On the adversarial robustness of multi- modal foundation models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem On the adversarial robustness of multi- modal foundation models,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.790355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 e7282216-4b44-4977-b5b9-b8be0604bc75 · outbound

This paper cites Stop reasoning! when multimodal llm with chain-of-thought reasoning meets adversarial image,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Stop reasoning! when multimodal llm with chain-of-thought reasoning meets adversarial image,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.801201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd3c201-7843-44fd-97ea-3194aec79589 · outbound

This paper cites The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.806066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1fad37e-374e-42ea-888c-2097df2347bd · outbound

This paper cites Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.811288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b18f63-9e7b-498e-86d4-c375b1cbc49f · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.817446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86be7ecb-38f4-498f-8602-f4fa2693123c · outbound

This paper cites Shadowcast: Stealthy data poisoning attacks against vision-language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Shadowcast: Stealthy data poisoning attacks against vision-language models,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.822542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2013fa-4567-474a-894e-f1846bb1a97a · outbound

This paper cites Towards Action Hijacking of Large Language Model-based Agent.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Towards Action Hijacking of Large Language Model-based Agent

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.827307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41199b9-8103-4ce2-b16f-939dd3d6b5c0 · outbound

This paper cites Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.832411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c41121bd-dd5c-450c-b2c2-01e94b63e8c4 · outbound

This paper cites Distract Large Language Models for Automatic Jailbreak Attack.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Distract Large Language Models for Automatic Jailbreak Attack

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.837912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600c0a24-c4b3-4a93-99fa-225f68e427c0 · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Tree of attacks: Jailbreaking black-box llms automatically,

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.843795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef6bd53-ea92-45d2-bf46-5eda0642c7d4 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.848760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1a58de-72c4-43f9-82c3-9319d8e37d06 · outbound

This paper cites Cold-attack: jailbreaking llms with stealthiness and controllability,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Cold-attack: jailbreaking llms with stealthiness and controllability,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.853904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4270c31d-b535-46c6-bf56-0b37b6020ce7 · outbound

This paper cites Automatically auditing large language models via discrete optimization,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Automatically auditing large language models via discrete optimization,

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.859620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efca184c-6882-477e-9c7a-1e48b2cfd1c0 · outbound

This paper cites An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.864656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e42f64e-6c4b-4976-b11b-ddec79a30121 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Sneakyprompt: Jailbreaking text-to- image generative models,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.870016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 811d6f14-528b-477a-9e4f-2297ddbc7f1a · outbound

This paper cites B-avibench: Towards evaluating the robustness of large vision-language model on black-box adversarial visual-instructions,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem B-avibench: Towards evaluating the robustness of large vision-language model on black-box adversarial visual-instructions,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.874836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff2f46d6-b0e7-454c-9188-346a70b12025 · outbound

This paper cites NetSafe: Exploring the Topological Safety of Multi-agent Networks.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem NetSafe: Exploring the Topological Safety of Multi-agent Networks

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.879479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4870ba2-6428-4aa8-a4ed-43cac6505500 · outbound

This paper cites LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.884636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f6d90c9-6877-4dab-9e19-61c99d98610d · outbound

This paper cites Attack prompt generation for red teaming and defending large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Attack prompt generation for red teaming and defending large language models,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.889570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e63365cc-f3de-4ebc-9ed4-0a92c9532ab9 · outbound

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

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.894305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7324bb-8228-4e7a-aae0-a10fdaa04c66 · outbound

This paper cites MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.901160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cccf4980-e510-4dc3-b34f-13addd08ef14 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.906505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e926332-086b-4f0f-a937-40ed7582bd46 · outbound

This paper cites Jailbreakbench: An open robustness benchmark for jailbreaking large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreakbench: An open robustness benchmark for jailbreaking large language models,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.912201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6165f2-9397-49e1-a1d3-073f93b321f4 · outbound

This paper cites Safety Assessment of Chinese Large Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Safety Assessment of Chinese Large Language Models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.917023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d22af0ba-5058-459f-b197-a9bad9e1af0c · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.922060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2580e79f-3449-4de1-a219-6373cc1c0811 · outbound

This paper cites Safetybench: Evaluating the safety of large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Safetybench: Evaluating the safety of large language models,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.927055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42506a14-1c93-4d5b-a36c-d22bfa1a4232 · outbound

This paper cites AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.931618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a127cf8-c980-4942-a603-06cdeaf79d3b · outbound

This paper cites Improved baselines with visual instruction tuning,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Improved baselines with visual instruction tuning,

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.936477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6f28d0-d2ae-427b-8695-2a1a945685a2 · outbound

This paper cites Xstest: A test suite for identifying exaggerated safety behaviours in large language models,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Xstest: A test suite for identifying exaggerated safety behaviours in large language models,

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.941077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a80c37-7277-4d39-807b-dbc2a444fdd8 · outbound

This paper cites Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.946166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd74cc92-39b9-4fef-86d7-15bbfedee185 · outbound

This paper cites A strongreject for empty jailbreaks,.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem A strongreject for empty jailbreaks,

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.951094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f3289407-400f-4fb2-9b4f-f90a42d14d90 · inbound

Why Do Large Language Models Generate Harmful Content? cites this paper.

Why Do Large Language Models Generate Harmful Content? From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:21:04.455333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 465afa0d-a6cf-4047-ab18-4f50a595cf03 · inbound

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing cites this paper.

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:08:26.230043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2f04d52b-1ccd-4a34-9e7d-81f586d33660 · inbound

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking cites this paper.

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:11.989368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f82069eb-b26d-4765-8629-ed7f50910404 · inbound

ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation cites this paper.

ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-21T10:04:58.937649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 183d512f-8525-4ef8-a2bf-694b927d5b79 · inbound

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks cites this paper.

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T00:32:00.146044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ccdeae-3182-49f1-9aa4-546293ccab5a · inbound

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains cites this paper.

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T19:28:46.534696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.