Paper Citation Record · LEDGER

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

As of 10 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 2 inbound Pith citation observations for arXiv:2505.22271.

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

pith.paper-citation-record.v1
2505.22271 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:17:25.808065Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T07:14:32.902738Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T07:24:22.504297Z

Reference resolution

58 of 58 outbound references displayed

verified exact1
verified fuzzy30
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0845ab38-c298-47da-892c-114ca7a9cc98 · outbound

This paper cites Jail- breaking black box large language models in twenty queries.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Jail- breaking black box large language models in twenty queries

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:32.148838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1c145bd4-d723-40d5-b022-ac9644772aa2 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:19.865083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f63183-8f51-498a-8548-e17478612deb · outbound

This paper cites Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 2024.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:32.006849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d8fdbdc4-059f-4bb3-9e02-b421cdfee5b9 · outbound

This paper cites Libre: A practical bayesian approach to adversarial detection.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Libre: A practical bayesian approach to adversarial detection

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:31.760169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28b528c5-886b-46d1-9e51-7b3eaa387197 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.181959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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

Reference 6

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a25ac3bc-1770-46f9-a19e-f3a7d20911e4 · outbound

This paper cites Eyes closed, safety on: Protecting multimodal llms via image-to-text transformation.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Eyes closed, safety on: Protecting multimodal llms via image-to-text transformation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:31.578334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 56d8d03a-0245-461d-8177-ffdcaf057196 · outbound

This paper cites Backdoor defense via test-time detecting and repairing.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Backdoor defense via test-time detecting and repairing

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:31.441131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94d78a55-b09e-488b-9eca-0cac1d718256 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models LoRA: Low-rank adaptation of large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:31.213043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ebd8e886-f4c4-4b3e-8b47-b31162f717af · outbound

This paper cites Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.682371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce751ab-57da-4788-b53e-d3e10dbe983f · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.741888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b125cd62-7fce-480b-90cf-ee3be2e2cfdc · outbound

This paper cites Mistral 7B.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Mistral 7B

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.801958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf4814e-1a02-44cf-b5bc-3f087104aea1 · outbound

This paper cites Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.arXiv preprint arXiv:2407.01599, 2024.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.arXiv preprint arXiv:2407.01599, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.872477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9945a9f-ca74-4f71-aefc-a281a6f69a1a · outbound

This paper cites A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925, 2023.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925, 2023

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:20.980016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49499c2f-bc9e-40e6-8a97-278451b82a47 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Adam: A Method for Stochastic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:21.040516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3eb8416-463e-4425-b4f4-9836979c048e · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Certifying LLM Safety against Adversarial Prompting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:21.099918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca613c9-a9fb-45e4-ba0a-58e1e7eaacc5 · outbound

This paper cites A comprehensive survey on test-time adaptation under distribution shifts.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models A comprehensive survey on test-time adaptation under distribution shifts

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.926981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f362cc21-f395-49d3-81e4-6932e4aa58b7 · outbound

This paper cites Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:17:26.486041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 56d86f8b-23fe-4037-8a6b-b44366b4e45b · outbound

This paper cites Microsoft coco: Common objects in context.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Microsoft coco: Common objects in context

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.735860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81052493-b28b-46d9-88a6-801b8ddb13c9 · outbound

This paper cites Visual instruction tuning.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Visual instruction tuning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.563054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ab48208f-11ce-47fd-b197-841d233cf260 · outbound

This paper cites Improved baselines with visual instruction tuning.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Improved baselines with visual instruction tuning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.388861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fb5e1d04-325b-44fd-af20-b51ab3eb58dc · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.185100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ad404526-d415-4378-923c-64374aeebaf4 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:30.018038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c9f5fa92-8fd8-4632-8983-76ee67e6b68d · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Mm-safetybench: A benchmark for safety evaluation of multimodal large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:29.858044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4bfeaadc-76ec-4cae-9a69-21bf527f2e44 · outbound

This paper cites A Comprehensive Overview of Large Language Models.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models A Comprehensive Overview of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:21.675739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4f2856b-434f-4975-a618-78152c1cfdb3 · outbound

This paper cites Dad: Data-free adversarial defense at test time.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Dad: Data-free adversarial defense at test time

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:29.660346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 114fc22b-ea06-41dd-bf1f-25ae276fc8d0 · outbound

This paper cites GPT-4 Technical Report.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models GPT-4 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:21.904633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb30a0ee-b326-4202-967c-4c6538b87461 · outbound

This paper cites Rapid Response: Mitigating LLM Jailbreaks with a Few Examples.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Rapid Response: Mitigating LLM Jailbreaks with a Few Examples

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:22.037860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e881e95e-9ce6-4fbb-bec8-4cd8c8fb43df · outbound

This paper cites Instruction Tuning with GPT-4.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Instruction Tuning with GPT-4

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:22.099259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a402bbf3-7b33-4adc-81cf-cdebf6a9d88b · outbound

This paper cites Llm self defense: By self examination, llms know they are being tricked.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Llm self defense: By self examination, llms know they are being tricked

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:29.519521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3455ac16-09e2-4e3f-ab96-c22cdccbcb4c · outbound

This paper cites Mllm-protector: Ensuring mllm’s safety without hurting performance.Proc.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Mllm-protector: Ensuring mllm’s safety without hurting performance.Proc

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:29.371293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 79190684-5be4-426e-ae99-3203d733c65a · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Visual adversarial examples jailbreak aligned large language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:29.226614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 167eb778-99ee-4038-858d-aa63acb0cbf6 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Improving language understanding by generative pre-training

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:22.646829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62efe873-765e-45cf-b857-39db2e329bc6 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models High-resolution image synthesis with latent diffusion models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:28.993222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8c15d46-d490-4f00-b15e-6831a2b9fa64 · outbound

This paper cites Protecting Model Adaptation from Trojans in the Unlabeled Data.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Protecting Model Adaptation from Trojans in the Unlabeled Data

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:17:26.238790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 712d64e6-8dba-4ac6-b879-9432bcf405f0 · outbound

This paper cites Learning to summarize with human feedback.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Learning to summarize with human feedback

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:28.789095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 78fe64cb-4df1-4848-8b0b-ecd21f5ca6ab · outbound

This paper cites Measuring the accuracy of diagnostic systems.Science, 240(4857):1285–1293, 1988.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Measuring the accuracy of diagnostic systems.Science, 240(4857):1285–1293, 1988

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:23.236378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0170707d-2eee-4bc2-9dd7-41195eac145e · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:23.436727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d51830-12ec-482c-bd20-d75863969f64 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:23.623355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03373f95-d0b4-4e6e-a721-de326268dd8a · outbound

This paper cites Tent: Fully test-time adaptation by entropy minimization.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Tent: Fully test-time adaptation by entropy minimization

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:28.596615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7cdfaab2-b3b9-4dd1-8864-4e0ee71cfc06 · outbound

This paper cites Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:23.839067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89992326-ccef-4775-a9f8-511491b8817f · outbound

This paper cites Defending llms against jailbreaking attacks via backtranslation.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Defending llms against jailbreaking attacks via backtranslation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:28.389761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 06907291-a297-44f6-9858-e073b879b825 · outbound

This paper cites Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:28.160634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 73d2de4a-8bd0-44b0-b6e4-7b1dec2610c8 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.102566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471dcb12-f247-4482-be11-f598d5a4218c · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.Nature Machine Intelligence, 5(12):1486–1496, 2023.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Defending chatgpt against jailbreak attack via self-reminders.Nature Machine Intelligence, 5(12):1486–1496, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.264935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc86ef63-d0e6-426b-afdd-275cea67d226 · outbound

This paper cites Gradsafe: Detecting jailbreak prompts for llms via safety-critical gradient analysis.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Gradsafe: Detecting jailbreak prompts for llms via safety-critical gradient analysis

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.939953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9ef5f3f6-8b65-46ac-a09b-3c2d6e8fde5a · outbound

This paper cites Wizardlm: Empowering large pre-trained language models to follow complex instructions.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Wizardlm: Empowering large pre-trained language models to follow complex instructions

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.801491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 83b8baf3-1190-47cd-a8ea-3fbfb5515aac · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.669043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5f35cc-4ef6-4d18-91ea-2720e37edaf4 · outbound

This paper cites Stamp: Outlier-aware test-time adaptation with stable memory replay.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Stamp: Outlier-aware test-time adaptation with stable memory replay

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.641319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b82128b5-df7b-4649-91c9-431c1e7cad3b · outbound

This paper cites Instruction tuning for large language models: A survey.arXiv preprint arXiv:2308.10792, 2023.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Instruction tuning for large language models: A survey.arXiv preprint arXiv:2308.10792, 2023

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.856171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb5be6a-e6e3-426e-8d88-ce0dd430be2c · outbound

This paper cites JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.937849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f98d0ec3-61f0-41e7-a35c-283aa7e4c457 · outbound

This paper cites Defending large language models against jailbreaking attacks through goal prioritization.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Defending large language models against jailbreaking attacks through goal prioritization

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.421311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ac80896e-fa10-4990-a10f-6527abf9c6b1 · outbound

This paper cites The first to know: How token distributions reveal hidden knowledge in large vision-language models? InProc.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models The first to know: How token distributions reveal hidden knowledge in large vision-language models? InProc

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.275094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1e8403bd-a55d-4ef7-9dc1-b40ee193785a · outbound

This paper cites A Survey of Large Language Models.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models A Survey of Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:25.320167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 637246e7-529b-4d42-a374-0a774e2dfdf5 · outbound

This paper cites Improved few-shot jailbreaking can circumvent aligned language models and their defenses.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Improved few-shot jailbreaking can circumvent aligned language models and their defenses

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:27.138624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7cb6da9d-22c6-4b49-9033-1ef6acbb4384 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Minigpt-4: Enhancing vision- language understanding with advanced large language models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:26.974341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5039fe24-3486-46e2-b31e-07ae8f4a358b · outbound

This paper cites Safety fine-tuning at (almost) no cost: A baseline for vision large language models.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Safety fine-tuning at (almost) no cost: A baseline for vision large language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:17:26.826571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4461d1a0-d860-431a-91e7-0ce83f9ad5b6 · outbound

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:25.808065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1b1d1d6c-e1c3-4414-b792-8952e4fd56f8 · inbound

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning cites this paper.

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:16:07.293158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca574ac8-d05a-48c1-b5d0-5f3862ed884f · inbound

On the Vulnerability of Parameter-Level Defenses to Model Merging cites this paper.

On the Vulnerability of Parameter-Level Defenses to Model Merging Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:24:22.505907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.