Paper Citation Record · LEDGER

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

As of 10 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 6 inbound Pith citation observations for arXiv:2506.12707.

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

pith.paper-citation-record.v1
2506.12707 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:51:17.376587Z

measured 64 of 64 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 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:26:33.740006Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy19
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation baaf0953-9590-45a4-816d-5129397a306b · outbound

This paper cites write newline.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.192495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f489e1d1-31f8-452d-a2f0-4778dede5cb4 · outbound

This paper cites Jailbreak chat.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbreak chat

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.259708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26314066-b5e4-49cd-bfae-18d455d64231 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Detecting Language Model Attacks with Perplexity

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.372566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 147ea0d0-fa22-4d2a-84e9-cf90cc15e8a6 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.452064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb845684-1e0a-4c48-8ad9-bf9e2db8eb0f · outbound

This paper cites Man ends his life after an ai chatbot ‘encouraged’ him to sacrifice himself to stop climate change, 2023.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Man ends his life after an ai chatbot ‘encouraged’ him to sacrifice himself to stop climate change, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:21.101319Z

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 1b213cf9-6f47-4671-b912-e3ca114fdcd4 · outbound

This paper cites Self-Evaluation as a Defense Against Adversarial Attacks on LLMs.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Self-Evaluation as a Defense Against Adversarial Attacks on LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.623444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69243559-1075-4b96-844a-4b9ad1f446fc · outbound

This paper cites Defending against alignment-breaking attacks via robustly aligned LLM.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Defending against alignment-breaking attacks via robustly aligned LLM

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.713377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a57ed3-c10d-40b1-acd4-43c05457a424 · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.803278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6fa1b9b-6103-4470-899c-91d1e6760f53 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbreakbench: An open robustness benchmark for jailbreaking large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:21.080126Z

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 03224b36-991f-4abe-a018-ec65c0c01ad0 · outbound

This paper cites Jailbreaking black box large language models in twenty queries.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbreaking black box large language models in twenty queries

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:12.987949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35d23faf-546e-4325-80f3-e34d7dbfa577 · outbound

This paper cites Secalign: Defending against prompt injection with preference optimization.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Secalign: Defending against prompt injection with preference optimization

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:21.048887Z

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 2f5e76b7-4496-4f3a-bdaa-b1f58f3101e9 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.135722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9f90cb-37a9-41cb-a017-4e726dced87c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Training Verifiers to Solve Math Word Problems

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.219044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b40237-dc9d-4493-8ffa-4d4640870fb4 · outbound

This paper cites Unsupervised cross-lingual representation learning at scale.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Unsupervised cross-lingual representation learning at scale

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.285840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 326ab2c2-cc5e-4c24-a545-a7234f74447e · outbound

This paper cites an unresolved cited work.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:51:21.033341Z

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 b604ea45-9d0f-4d8b-872c-dc0f7479c980 · outbound

This paper cites Attacking Large Language Models with Projected Gradient Descent.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Attacking Large Language Models with Projected Gradient Descent

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.446894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 895e0d50-d167-4d18-8560-ca8da4537bb3 · outbound

This paper cites Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.486563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e306f66-3262-43ed-bffb-08144fea8576 · outbound

This paper cites Measuring massive multitask language understanding.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Measuring massive multitask language understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.554155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 248e56c6-3f70-48fd-a41c-9c01037a539c · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.637419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827b136a-77a5-438e-86cd-fc160fb6551a · outbound

This paper cites Disaster-tweet-jailbreaking.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Disaster-tweet-jailbreaking

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:21.004464Z

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 5c6a32ac-e799-43ad-bf00-a6efd8502210 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.818052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377b48aa-47e9-4eee-be41-0e4328e2ad8d · outbound

This paper cites Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.884686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4fac2f2-b8a9-4f4c-a379-ba321fd7a8a7 · outbound

This paper cites LLML ingua: Compressing prompts for accelerated inference of large language models.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression LLML ingua: Compressing prompts for accelerated inference of large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:13.956196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c675a59-edbc-4d8d-b4c2-38d5b4883d33 · outbound

This paper cites L ong LLML ingua: Accelerating and enhancing LLM s in long context scenarios via prompt compression.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression L ong LLML ingua: Accelerating and enhancing LLM s in long context scenarios via prompt compression

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.985875Z

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 06f31ebc-dc8a-4328-ab4b-fad372c5bbd7 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.967339Z

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 9414708c-1bcc-4d8c-a4f5-0045fe104b16 · outbound

This paper cites RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:14.208331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f1b166-92c3-4cfd-acb3-0c09c8e37ae9 · outbound

This paper cites Certifying llm safety against adversarial prompting.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Certifying llm safety against adversarial prompting

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.864427Z

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 d455e029-ca7f-4c7b-b35d-5e8919c35bbf · outbound

This paper cites Uncensor any llm with abliteration.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Uncensor any llm with abliteration

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.781505Z

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 b96be9cb-eafe-43eb-900a-0210cb5a6c74 · outbound

This paper cites Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:14.442961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84b889f3-af8b-4806-a2fa-36cdd139cc3b · outbound

This paper cites Compressing context to enhance inference efficiency of large language models.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Compressing context to enhance inference efficiency of large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.619602Z

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 e2e7ee43-43d4-4af9-9969-29efd5d04e05 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:14.630658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16bef299-4bc9-4fd5-870e-fa210052aa89 · outbound

This paper cites Jailbreakv-28k: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbreakv-28k: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.439743Z

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 18e830a5-1c9e-49c5-830e-f548d61b9f1b · outbound

This paper cites Whoops, samsung workers accidentally leaked trade secrets via chatgpt, 2023.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Whoops, samsung workers accidentally leaked trade secrets via chatgpt, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:20.202986Z

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 4c1be3ea-459e-4f2b-b03b-57f739af2809 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Tree of attacks: Jailbreaking black-box llms automatically

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:19.894291Z

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 764837be-d5f6-4ddb-87ac-cbc9ea754d0c · outbound

This paper cites Vicky Zhao, Lili Qiu, and Dongmei Zhang.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Vicky Zhao, Lili Qiu, and Dongmei Zhang

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:19.523449Z

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 f13318f7-9d9b-43a9-85a7-4a8ca417ab61 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Llm self defense: By self examination, llms know they are being tricked

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:19.310019Z

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 0cc4225b-3b8b-4530-a3c1-a9337ad483f5 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Visual adversarial examples jailbreak aligned large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:19.063474Z

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 48d788cd-28d7-474d-bf47-f2b11d731344 · outbound

This paper cites Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.291406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da9f398d-fc48-4c1c-9fc2-75f43959fecc · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Gpqa: A graduate-level google-proof q&a benchmark

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.423377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87cace88-da85-435a-be2c-8c912a16319c · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.538793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4caf03b7-64e8-467e-aa4e-56422e420bb6 · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.645320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dd622fd-0bb5-4274-94fb-a181352e29ee · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.725633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd2e3a8-424b-4c80-bd39-4c7fc7cb5cf5 · outbound

This paper cites do anything now.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression do anything now

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.830933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47cef48-d024-4d6f-b0d9-0a874c8b7f6f · outbound

This paper cites Hashimoto.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Hashimoto

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:15.922905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aab340f4-45dd-49f3-90fb-fabd62f572e1 · outbound

This paper cites Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants, 2023.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants, 2023

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.023673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7f9f0db-eb93-48dd-a65b-b4b551a8985f · outbound

This paper cites Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, D.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, D

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:18.794631Z

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 11f9dcbc-aef6-4846-97cc-a344d846d212 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression The art of defending: A systematic evaluation and analysis of LLM defense strategies on safety and over-defensiveness

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.249173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9161acc-3971-45be-b16c-cf948c7ac867 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36: 0 80079--80110, 2023.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36: 0 80079--80110, 2023

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.359520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413a4647-048e-4441-9371-c7cafcb571e2 · outbound

This paper cites S afe D ecoding: Defending against jailbreak attacks via safety-aware decoding.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression S afe D ecoding: Defending against jailbreak attacks via safety-aware decoding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.432787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e9970a-9821-4ea5-8785-6a6c1e4b9e9a · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.537098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb7886b4-1e26-4aca-862a-fd139d5c1143 · outbound

This paper cites Rigorllm: Resilient guardrails for large language models against undesired content.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Rigorllm: Resilient guardrails for large language models against undesired content

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:18.572531Z

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 0f3f3c27-474a-4b3b-b61b-6f317dc50678 · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:18.361528Z

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 96fd0665-3084-4a7e-82af-daa38dcc1b51 · outbound

This paper cites AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:16.836659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b12714fd-2706-4a8f-8621-ab7bfaef5d1d · outbound

This paper cites Intention analysis makes LLM s a good jailbreak defender.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Intention analysis makes LLM s a good jailbreak defender

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:51:18.152088Z

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 6dbf2248-967e-4e18-bcec-1529caef66fb · outbound

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

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:17.027160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b06e34-8908-4d18-9a28-976c6ff296cb · outbound

This paper cites @esa (Ref.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression @esa (Ref

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:17.136097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc5b558-5d05-48db-bd47-dc84be8b9f28 · outbound

This paper cites an unresolved cited work.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:17.232839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8143df8a-b0ce-49dd-bf9e-26453b94e2a9 · outbound

This paper cites Ambiguity.

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression Ambiguity

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:17.376587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 78eea0d0-1fe4-4800-b901-e33be6914de4 · inbound

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey cites this paper.

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 126

Resolution: unresolved; no resolver link, observed 2026-08-05T15:26:33.740006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1974b8-814b-4282-b00b-bfa6a7344c55 · inbound

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation cites this paper.

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T12:51:33.363099Z

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 4a95b1bd-351a-49d4-9c69-64c0710fefc5 · inbound

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks cites this paper.

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:08:00.786991Z

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 611ce5a7-5f92-40cc-ab62-57dc1a310da4 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.317171Z

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 1784d372-d12a-44cc-a282-e3e6a6cd1943 · inbound

Prompt Governance? On Governing Technologies Governed by Natural Language cites this paper.

Prompt Governance? On Governing Technologies Governed by Natural Language SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 193

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:25:32.933322Z

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 e49c6208-7c87-4509-8609-7c19ad7b1c60 · inbound

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks cites this paper.

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T01:16:14.920942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.