Paper Citation Record · LEDGER

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

As of 8 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 3 inbound Pith citation observations for arXiv:2505.15753.

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

pith.paper-citation-record.v1
2505.15753 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:15:48.828674Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:55:01.175611Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-19T11:37:15.922072Z

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy16
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 99b7ab13-ce2b-460a-adf7-242f3bd5d271 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Detecting Language Model Attacks with Perplexity

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.522821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb68cd4-3423-4fb7-946d-878e2646fb5f · outbound

This paper cites RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.529201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64ceb1b-9e7c-49c2-a707-4a12513aec4c · outbound

This paper cites Qwen technical report.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Qwen technical report

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:52.609923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 886a8169-04ba-48e4-b2e7-e55a244fca48 · outbound

This paper cites Constitutional ai: Harmlessness from ai feedback, 2022.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Constitutional ai: Harmlessness from ai feedback, 2022

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.540149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45cab46-1d09-4a98-879c-4da8a4448c56 · outbound

This paper cites Safeinfer: Context adaptive decoding time safety alignment for large language models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Safeinfer: Context adaptive decoding time safety alignment for large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:52.384358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98ec7c4c-dc42-4b15-8d62-997bdb9eb3a4 · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.550190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d460c8a-66b5-425c-ac4e-76febce85e8c · outbound

This paper cites Towards the worst-case robustness of large language models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Towards the worst-case robustness of large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.555459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1712231-c99f-48e3-a1a8-e34fb7c9b811 · outbound

This paper cites Evaluating large language models trained on code, 2021.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Evaluating large language models trained on code, 2021

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:52.170794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3db68c66-159c-4920-bc1a-6c8fe9a743c8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.565245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00503b70-36cd-4723-bc38-02c821a144c7 · outbound

This paper cites Safe rlhf: Safe reinforcement learning from human feedback.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Safe rlhf: Safe reinforcement learning from human feedback

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:51.667541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 316fc115-9d99-4232-b4e7-4d35eac70880 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Multilingual Jailbreak Challenges in Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.577618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a248c4bd-a27b-4259-ab97-eee247e8dff8 · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.584004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e1a44d9-31bf-422e-b958-1cae8ab91900 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.589805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f58024da-2a64-4c2a-adc5-c54e21b63d16 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Explaining and Harnessing Adversarial Examples

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.594740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6df03e-c5fc-4ac7-808a-95433d683301 · outbound

This paper cites The Llama 3 Herd of Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.601205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5520535c-e1fb-4184-9649-3fd34870b845 · outbound

This paper cites Measuring massive multitask language understanding.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Measuring massive multitask language understanding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.605873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52d6f016-d02b-4072-953a-d445c93b68cd · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.609882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8206a2c-c27e-4148-b506-cd9e25c144b1 · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.615884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f64e1a99-04dc-4715-9a5d-43ae87f3f4c1 · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval AI Alignment: A Comprehensive Survey

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.621390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8729fdfa-68d5-4471-96b8-893b157485b5 · outbound

This paper cites Improved Techniques for Optimization-Based Jailbreaking on Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.626254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1995933e-f583-4470-a0a7-35dbd5bd062b · outbound

This paper cites Mistral 7B.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Mistral 7B

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.631589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31bca02c-52af-4830-80f1-59a011fa3116 · outbound

This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Artprompt: Ascii art-based jailbreak attacks against aligned llms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.636714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14b50c3f-e2d8-42a3-b948-a0a6529ea65f · outbound

This paper cites Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models, 2024.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.641406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40304df-a0f8-432a-a08a-754a4a82db50 · outbound

This paper cites Dense passage retrieval for open-domain question answering.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Dense passage retrieval for open-domain question answering

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.646827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c615d12-22ed-4350-9a2f-985701feaae0 · outbound

This paper cites Buckley, Jason Phang, Samuel R.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Buckley, Jason Phang, Samuel R

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:51.316907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5df0e263-d0cd-4aa3-ae20-573e45d7e151 · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.657664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e0be59-58ec-4d49-8f45-4ca9174e2b49 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Retrieval-augmented generation for knowledge-intensive nlp tasks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.663277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a32c2e-917c-475f-8bbb-020ed343ffbf · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.669536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c73d0b-3953-49fd-9b60-d83085a05ea3 · outbound

This paper cites Towards General Text Embeddings with Multi-stage Contrastive Learning.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Towards General Text Embeddings with Multi-stage Contrastive Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.674872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b586a7-03a1-453f-aca6-8674ddee56fb · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.679903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 417498db-a5c1-4c68-af90-e1fe302d606b · outbound

This paper cites Jailbreaking chatgpt via prompt engineering: An empirical study, 2023.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Jailbreaking chatgpt via prompt engineering: An empirical study, 2023

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:51.112343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e2a2a90-9575-48b8-b1c4-1c77ed3fe5db · outbound

This paper cites Harmbench: A standardized evaluation framework for automated red teaming and robust refusal.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Harmbench: A standardized evaluation framework for automated red teaming and robust refusal

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.690350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a42ad48c-47f4-4623-a68e-88ac9302a7cd · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems , 37:61065–61105, 2024.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems , 37:61065–61105, 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:51.015657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f9dd6051-07a6-4c12-9962-15a75bfd8fe9 · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Rapid Response: Mitigating LLM Jailbreaks with a Few Examples

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.700337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38744573-a46d-4814-aaf5-834a00156e4a · outbound

This paper cites Position: Adversarial ML for LLMs Is Not Making Any Progress.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Position: Adversarial ML for LLMs Is Not Making Any Progress

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.706076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13e1fa99-f5d6-49d1-923f-23fd1959b7b9 · outbound

This paper cites The probabilistic relevance framework: Bm25 and beyond.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval The probabilistic relevance framework: Bm25 and beyond

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.918748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2a0ec857-ce8b-41a3-875c-f07ea6f12cb2 · outbound

This paper cites Mitigating skeleton key, a new type of generative ai jailbreak technique.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Mitigating skeleton key, a new type of generative ai jailbreak technique

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.810370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f15bcb96-d1a4-4fa6-8051-2dbd064f51c2 · outbound

This paper cites Fine-tuning mistral 7b large language model for python query response and code generation: A parameter efficient approach.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Fine-tuning mistral 7b large language model for python query response and code generation: A parameter efficient approach

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.720684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5bc4c4e-73aa-49d1-bfac-37998a2d099f · outbound

This paper cites Intriguing properties of neural networks.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Intriguing properties of neural networks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.725718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07420015-32fa-4fbc-a748-10cfb72eab27 · outbound

This paper cites A theoretical understanding of self-correction through in-context alignment.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval A theoretical understanding of self-correction through in-context alignment

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.669636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ed33eb3c-588d-40f4-b5d4-4f68de34dea2 · outbound

This paper cites Reinforcement Learning for LLM Post-Training: A Survey.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Reinforcement Learning for LLM Post-Training: A Survey

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.734701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bedce304-5b00-4bfa-a80b-78b18299dbf8 · outbound

This paper cites Jailbroken: How does llm safety training fail? In NeurIPS, 2023.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Jailbroken: How does llm safety training fail? In NeurIPS, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.569860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9bdd8198-b371-4ea6-b84c-bdc93100f652 · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.745729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80923eb6-3302-4e01-aefa-cd38a4aa9859 · outbound

This paper cites Certifiably robust rag against retrieval corruption.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Certifiably robust rag against retrieval corruption

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.750950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f959c3cd-4489-4b6b-a410-054ac506d400 · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Defending chatgpt against jailbreak attack via self-reminders

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.756297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f2115bb-ba62-431e-b74f-8fc169eb8c44 · outbound

This paper cites Safedecoding: Defending against jailbreak attacks via safety-aware decoding.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Safedecoding: Defending against jailbreak attacks via safety-aware decoding

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.435836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d7afac52-f6a5-4c8d-ab70-f10d27949b6a · outbound

This paper cites BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.764754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2e0e766-d937-4532-ba55-fbcc41433d8d · outbound

This paper cites GPT-4 is too smart to be safe: Stealthy chat with LLMs via cipher.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval GPT-4 is too smart to be safe: Stealthy chat with LLMs via cipher

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.261654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98157b43-ce31-4c47-8cb9-741cf18ad1b1 · outbound

This paper cites The ai alignment problem: why it is hard, and where to start.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval The ai alignment problem: why it is hard, and where to start

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.774898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4648f707-0efa-4133-9d6f-04b7ed3ff604 · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:50.030436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 80e84f86-572f-43b4-adf7-e09f88940881 · outbound

This paper cites Boosting jailbreak attack with momentum.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Boosting jailbreak attack with momentum

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:49.714847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 252c035a-fe45-41e2-80c2-4547273f67ef · outbound

This paper cites Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.790118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde56ada-4e21-4d97-9e75-fc1a3582ac16 · outbound

This paper cites On prompt-driven safeguarding for large language models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval On prompt-driven safeguarding for large language models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:49.528671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dee30cea-29b1-40b1-b489-8b9ad2672dad · outbound

This paper cites Poisoning Retrieval Corpora by Injecting Adversarial Passages.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Poisoning Retrieval Corpora by Injecting Adversarial Passages

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.802863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4007808-2e3a-4b2b-9c68-e66246ff8219 · outbound

This paper cites Trustworthiness in Retrieval-Augmented Generation Systems: A Survey.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.809235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94337f36-ae35-4de6-9ad1-7e7532814868 · outbound

This paper cites ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.816711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d43d4a-9670-4242-8b07-6e026f2d3d14 · outbound

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.822543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26e778b4-da45-4896-8dfd-0f438f6e2eee · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.828674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d0e4b5aa-4b40-4323-bfb8-6848d43a9507 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:37:15.923828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d7f6248-08d0-45b0-8e87-2bc492581934 · inbound

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring cites this paper.

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T22:31:19.445142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a6d4da1b-bd9f-48fb-aa91-94f1b4938306 · inbound

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions cites this paper.

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-01T18:55:01.175611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.