Paper Citation Record · LEDGER

JavelinGuard: Low-Cost Transformer Architectures for LLM Security

As of 17 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 1 inbound Pith citation observation for arXiv:2506.07330.

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

pith.paper-citation-record.v1
2506.07330 v1

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:41:25.552737Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T15:05:08.411286Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T22:46:19.226413Z

Reference resolution

60 of 60 outbound references displayed

verified exact0
verified fuzzy10
unresolved50
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7100632c-ff3f-474d-990f-65599ab8012a · outbound

This paper cites Get my drift? Catching LLM Task Drift with Activation Deltas.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.315260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ebaf00-672b-4d55-be47-85964245d851 · outbound

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

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.319900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca91e754-c95b-4559-a478-edc26ac4d113 · outbound

This paper cites Longformer: The Long-Document Transformer.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Longformer: The Long-Document Transformer

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.323891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9567dc39-c0be-4ab2-a78f-14ba55a4a456 · outbound

This paper cites EuroBERT: Scaling Multilingual Encoders for European Languages.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security EuroBERT: Scaling Multilingual Encoders for European Languages

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.328485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b0a6d3-d12f-4175-8ce8-cf477bd835c9 · outbound

This paper cites NeoBERT: A Next-Generation BERT.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security NeoBERT: A Next-Generation BERT

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.332545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678082c1-45cf-4324-a007-99bccd950c09 · outbound

This paper cites Pappas, and Eric Wong.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Pappas, and Eric Wong

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.336740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6277d0de-5d2c-4458-bb27-da4173afcf3d · outbound

This paper cites Defense Against Prompt Injection Attack by Leveraging Attack Techniques.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Defense Against Prompt Injection Attack by Leveraging Attack Techniques

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.340870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a960944a-cdbe-4137-8087-c0fdfa07eae6 · outbound

This paper cites Rethinking Attention with Performers.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Rethinking Attention with Performers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.345503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cace89d0-a430-42c3-b66f-0ebdada37f3f · outbound

This paper cites Deepset prompt injection guardrail, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Deepset prompt injection guardrail, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.306114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 918f6875-290b-45de-aa05-f5e0aacc7e4e · outbound

This paper cites Duoguard: A two-player rl-driven framework for multilingual llm guardrails, 2025.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Duoguard: A two-player rl-driven framework for multilingual llm guardrails, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.353875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5996d375-da0b-47e3-a050-ed7eec657248 · outbound

This paper cites garak: A Framework for Security Probing Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security garak: A Framework for Security Probing Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.356935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17ad33d-2543-4776-a32d-89b0a4ddd171 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.361264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a876e8a2-bd42-41ed-8c37-11b70302d15c · outbound

This paper cites A wolf in sheep's clothing: Generalized nested jailbreak prompts can fool large language models easily, 2023.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security A wolf in sheep's clothing: Generalized nested jailbreak prompts can fool large language models easily, 2023

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.365277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d70c8ca-0dca-434a-a684-49d64b523cee · outbound

This paper cites h4rm3l: A language for Composable Jailbreak Attack Synthesis.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security h4rm3l: A language for Composable Jailbreak Attack Synthesis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.368455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0008caae-1c81-43a3-b732-85fcafad3a51 · outbound

This paper cites Fmops prompt injection guardrail, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Fmops prompt injection guardrail, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.289650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 65c83966-1ce6-4228-bb4b-5cfabc2683bf · outbound

This paper cites Improved Large Language Model Jailbreak Detection via Pretrained Embeddings.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Improved Large Language Model Jailbreak Detection via Pretrained Embeddings

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.376227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a02c637-236b-48bc-9429-84998efa3c15 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.380511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79cd9546-390d-4c6a-87c8-04a900acd5fb · outbound

This paper cites The Llama 3 Herd of Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.384612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380c2f49-cae7-41c3-8a19-2e3546abfedc · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.389280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139aa9e9-ccfe-4153-a64b-c272d21b0447 · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.392879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bfc8f48-a756-45a1-9d77-45534fa3abc8 · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.397072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad7c973f-bb55-4516-a42c-b4caed499c07 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.400701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51fc5fdb-b481-4602-85ef-d9687a80ef8b · outbound

This paper cites Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.404633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb4d93b-ad9b-4a88-a555-149af2568ed9 · outbound

This paper cites Best-of-N Jailbreaking.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Best-of-N Jailbreaking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.408036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb5367b-8781-4928-bfc9-7a99b2465ab7 · outbound

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

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.411365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9e816b9-6a8f-421f-a1db-9f3116b1adee · outbound

This paper cites Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.415816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 410026cd-3f9f-4d39-9f22-e2c59ed3f11c · outbound

This paper cites Lakera-guard, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Lakera-guard, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.279215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2b4a2a08-6a1f-44f4-8243-56230774416b · outbound

This paper cites InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.422926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdd77a0-996b-4739-bb66-7546694a0b4e · outbound

This paper cites SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.431089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 330eef9b-b172-4600-80f0-212d3ba113d2 · outbound

This paper cites Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation, 2023.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation, 2023

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.268900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ac873b87-a630-4489-9957-ac37cca69be5 · outbound

This paper cites Lost in the Middle: How Language Models Use Long Contexts.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Lost in the Middle: How Language Models Use Long Contexts

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.439015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3afdebdd-3f5e-4b72-9cbc-eccb2bbb06a5 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.442964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7345811-4137-43a4-b338-a49484f5d123 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses, 2024 b.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Formalizing and benchmarking prompt injection attacks and defenses, 2024 b

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.446488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b375a34-9b3e-4932-a5e8-e17de067a432 · outbound

This paper cites Promptguard prompt injection guardrail, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Promptguard prompt injection guardrail, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.256759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e45241f8-8ebd-45f5-b39e-5051199e0250 · outbound

This paper cites Granite Guardian.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Granite Guardian

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.455039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b212c15-719f-48a6-b0fc-ead3d45c34d3 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Ignore Previous Prompt: Attack Techniques For Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.458988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31b87016-bfe2-4f07-b9ae-fa4a118254d0 · outbound

This paper cites Fine-tuned deberta-v3-base for prompt injection detection, 2024 a.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Fine-tuned deberta-v3-base for prompt injection detection, 2024 a

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.244784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e629842-48bc-48f9-8fe6-206a3523b2d6 · outbound

This paper cites Fine-tuned deberta-v3-base for prompt injection detection, 2024 b.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Fine-tuned deberta-v3-base for prompt injection detection, 2024 b

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.232332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 529f57a7-1efa-43c9-9fa3-97c2cedc1141 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.469886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaef1318-e025-4719-b3e6-875569d1de59 · outbound

This paper cites NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.473951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35009d95-66aa-4b6f-83aa-3f26744e32df · outbound

This paper cites Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.478376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041865a1-7169-4108-9207-5d1b3a5aee40 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.482732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8030e0e-bc31-409a-b35c-b78a0376e43a · outbound

This paper cites ``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security ``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.222484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f2c8128a-0674-4de9-b909-8351da0a6d26 · outbound

This paper cites Optimization-based Prompt Injection Attack to LLM-as-a-Judge.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Optimization-based Prompt Injection Attack to LLM-as-a-Judge

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.489612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbedd655-a9e4-41ac-ac32-99b06d2f84fb · outbound

This paper cites A party of foundation models, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security A party of foundation models, 2024

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.211891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e6ce1a9c-425f-482a-945f-f58f49547b5d · outbound

This paper cites Alert: A comprehensive benchmark for assessing large language models' safety through red teaming, 2024.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Alert: A comprehensive benchmark for assessing large language models' safety through red teaming, 2024

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.497130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71b49a1-7392-4df8-80af-f4a4e28d0588 · outbound

This paper cites Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.500880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f53a5bc6-f00d-4a81-87a5-1bc33515624c · outbound

This paper cites Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.504822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4713d05-f5a1-4f04-ac63-5a6e06c47832 · outbound

This paper cites Defending LLMs against Jailbreaking Attacks via Backtranslation.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Defending LLMs against Jailbreaking Attacks via Backtranslation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.509264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31fee075-afa3-4a8a-b3e1-2d7eeb518f39 · outbound

This paper cites Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.514146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e864e9e-421f-4698-a545-2841e7642b3f · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Jailbroken: How Does LLM Safety Training Fail?

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.517829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45aae516-53f2-4d72-86fc-0dc9f1494bd5 · outbound

This paper cites an unresolved cited work.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.522448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1885a77b-acf8-4ed0-bd2d-6a19a4d708c2 · outbound

This paper cites Fundamental Limitations of Alignment in Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Fundamental Limitations of Alignment in Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.526186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0693264-866e-4e60-9f8e-589c4dda26a7 · outbound

This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.529733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45cea3df-5075-46fc-a1fc-386817c55935 · outbound

This paper cites LLM-Fuzzer : Scaling assessment of large language model jailbreaks.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security LLM-Fuzzer : Scaling assessment of large language model jailbreaks

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:41:26.187261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b22dcf5c-983d-4bf2-a0dd-31adf20acd47 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.536496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9bf3071-677e-4ee8-b44e-00b3661b94b0 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.540312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf5e83f1-5c39-4c93-8e80-7d2b2bd3d55f · outbound

This paper cites Defending Jailbreak Prompts via In-Context Adversarial Game.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Defending Jailbreak Prompts via In-Context Adversarial Game

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.544626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492e0e5a-2a9e-403c-ad88-6b7f8e6e2492 · outbound

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

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.548660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09c7b8f0-600e-4068-9bc2-b468114b3fc6 · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Improving Alignment and Robustness with Circuit Breakers

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.552737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 63c3cfb0-b070-4509-9a78-eda74b8e5795 · inbound

Gate AI: LLM Security Benchmark Evaluation Methodology and Results cites this paper.

Gate AI: LLM Security Benchmark Evaluation Methodology and Results JavelinGuard: Low-Cost Transformer Architectures for LLM Security

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:46:19.228179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.