Paper Citation Record · LEDGER

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

As of 14 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 11 inbound Pith citation observations for arXiv:2506.14922.

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

pith.paper-citation-record.v1
2506.14922 v2

Coverage vector

measured 81 of 81 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:15:06.220568Z

measured 92 of 92 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:06.502014Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T23:05:44.214387Z

Reference resolution

81 of 81 outbound references displayed

verified exact3
verified fuzzy7
unresolved70
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 902005c0-a4bb-49ec-863e-b22bac3f366a · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.134066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba14837-6435-4ee1-9a74-74a1cc5252fe · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:12.321056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8e59b1c9-3d35-4c85-85fd-6b86619fbecd · outbound

This paper cites Frontier AI Regulation: Managing Emerging Risks to Public Safety.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Frontier AI Regulation: Managing Emerging Risks to Public Safety

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.360822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f4db15-2b9f-4e52-b617-968d27336c8c · outbound

This paper cites Andriushchenko, A.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Andriushchenko, A

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:11.738324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a2c3b620-94b7-41e8-868b-7dd4fbfb1790 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:11.528965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 96a0fdd6-e0aa-40e1-ba3e-9dba35615d03 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.613791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc749e79-e13d-451d-a72f-9e72f0d65552 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Constitutional AI: Harmlessness from AI Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.695821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92ebef6-c1eb-404c-a7c3-8e94b9495b8c · outbound

This paper cites Sabotage Evaluations for Frontier Models.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Sabotage Evaluations for Frontier Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.781525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58871a79-1bcb-4d20-b6d9-c0c14da603d6 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:11.276627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cfba1cf5-35fd-49e4-81d5-182a7d296090 · outbound

This paper cites Explore, Establish, Exploit: Red Teaming Language Models from Scratch.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:59.966022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431efbee-a0bf-4b5a-afeb-9201798372a1 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.068299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1435b38-2ac7-4d75-82b9-7cb771fcbf99 · outbound

This paper cites Cui, W.-L.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Cui, W.-L

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:11.089615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1dc6ab61-8f0d-45ba-9099-4393c1c7f81a · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:10.926992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3f5d76a-8548-44c7-a635-c4a614e5d972 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.293871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf375f27-bace-47e8-920b-b61d9565dc55 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.379355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d795c97-49bb-4593-8c82-ed9875ae1870 · outbound

This paper cites MART: Improving LLM Safety with Multi-round Automatic Red-Teaming.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.457694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb50952-d1d9-413d-be5e-82a3066116a6 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Attacking Large Language Models with Projected Gradient Descent

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.545572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2513c89-8d5f-42a1-a973-4811b3530d72 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.611082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bafb0ea-20f1-4ed1-a1d2-10feb98f3ada · outbound

This paper cites Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.695930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e068781-6fc4-41cc-92c9-b1fae0262414 · outbound

This paper cites Claude 2.1 refuses to kill a python process: Hacker news.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Claude 2.1 refuses to kill a python process: Hacker news

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:10.774412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 558a4be8-c1f9-4951-9438-ffd6610a802b · outbound

This paper cites An Overview of Catastrophic AI Risks.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety An Overview of Catastrophic AI Risks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.870782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97587ca-13d7-4ce3-b7da-214a50e6e914 · outbound

This paper cites FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:07.454159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8ff9d318-5134-4de2-a3cc-14e3bb31ba07 · outbound

This paper cites Jailbreaking to Jailbreak.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Jailbreaking to Jailbreak

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.031229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8790198c-cfc5-4bb9-84bc-f284d8110a6b · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.139782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39f06acd-dc2b-4476-b7be-6502b5015fce · outbound

This paper cites ELITE: Enhanced Language-Image Toxicity Evaluation for Safety.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.258162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ede0a1-db21-4176-b312-ae2c7494631a · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:10.561222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d5622b38-d1cb-47b7-9f96-0a23a7be94db · outbound

This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.464128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19295399-2234-487e-94eb-73a7fedfedbe · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:10.382498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 55c53a0f-8d3b-4116-9f03-0f915f2a3bf7 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.602812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 199c33c7-2d7b-4d29-bce2-ebe622b4ac5f · outbound

This paper cites Large Language Model Unlearning via Embedding-Corrupted Prompts.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Large Language Model Unlearning via Embedding-Corrupted Prompts

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.670528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6223093a-3c22-47d2-82ef-f45af762f462 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.751718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39220523-c287-4ec3-af35-b8ea997ac126 · outbound

This paper cites LongSafety: Evaluating Long-Context Safety of Large Language Models.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety LongSafety: Evaluating Long-Context Safety of Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.810686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a40b2ff7-1ead-491d-974a-bc216dda5ecb · outbound

This paper cites Maini, S.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Maini, S

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.891368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10498fd5-ae2b-48cf-9c57-cbc237cc3147 · outbound

This paper cites PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.975098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2633b22d-f2d7-488a-a871-d96e0880e6af · outbound

This paper cites Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.056142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db69e234-0acf-4c5e-b8ff-95a91ea67b15 · outbound

This paper cites Mazeika, A.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Mazeika, A

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:10.217342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5f328571-72eb-4cf1-a071-846ce815c334 · outbound

This paper cites Mazeika, L.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Mazeika, L

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.159578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b534323-c059-406b-8c99-c41e3394168f · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.273880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4401b9eb-5aae-44ac-8b0e-81b114e01318 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:10.007223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation faab82b1-70ff-48c5-844f-faed07f25740 · outbound

This paper cites Unmasking the Canvas: A Dynamic Benchmark for Image Generation Jailbreaking and LLM Content Safety.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unmasking the Canvas: A Dynamic Benchmark for Image Generation Jailbreaking and LLM Content Safety

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:07.029969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eabf7516-1574-4ef7-a289-69224a8f4020 · outbound

This paper cites Ai risk management framework, May 2025.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Ai risk management framework, May 2025

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:09.836461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7a192034-1d69-451e-b82c-1abddea95343 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Training language models to follow instructions with human feedback

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.565572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f01772e-4044-4553-9783-09caad90b039 · outbound

This paper cites BBQ: A Hand-Built Bias Benchmark for Question Answering.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety BBQ: A Hand-Built Bias Benchmark for Question Answering

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.600768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d9b23e0-ef5f-4e81-9738-c8deef8f89dd · outbound

This paper cites Perez, S.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Perez, S

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.670676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0bf45fc-6d2a-4a3f-ae5e-fa2d2487a1b5 · outbound

This paper cites Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:06.783709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b8ec373d-df04-4667-9324-e12fa0240a54 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:09.654930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 47b59021-9a82-4245-a4bc-616a63c0094f · outbound

This paper cites LLM Safety for Children.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety LLM Safety for Children

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:02.902460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d6022c-0ec4-46d1-b49e-3abf3280731d · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.011329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4a944b9-7dd5-4bb7-9f03-2070e7a327f3 · outbound

This paper cites Representation Noising: A Defence Mechanism Against Harmful Finetuning.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Representation Noising: A Defence Mechanism Against Harmful Finetuning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.070633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722bac10-5e12-4d5b-8a26-f6d7c5d45045 · outbound

This paper cites Röttger, H.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Röttger, H

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.137214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92fff33d-915e-4c8d-85e5-1d1ba5e4463d · outbound

This paper cites Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.205891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1f431e-15c9-449b-9476-2a49f39b882d · outbound

This paper cites Revisiting the Robust Alignment of Circuit Breakers.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Revisiting the Robust Alignment of Circuit Breakers

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.295166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc4e0304-630b-4fb6-b532-bed6d3638f3c · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.395315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b239cc3b-6c8c-4e70-aa49-99e105369efd · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.455500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f77eac-3b4b-4899-beee-a46cbdabb3fd · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.520030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c141fa-d078-4021-bb6f-e7db47f87ed8 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.558005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5b34a33-ea5f-4996-8a38-e51418526272 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.649439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ac81ce7-660f-4fef-bd24-e4a98aaac07d · outbound

This paper cites PAL: Proxy-Guided Black-Box Attack on Large Language Models.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety PAL: Proxy-Guided Black-Box Attack on Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.747220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1070809-e116-432a-89a3-b27e81dd683c · outbound

This paper cites Souly, Q.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Souly, Q

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:09.487659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b510da0-9c43-47a4-af2c-75ed784a0f26 · outbound

This paper cites Sumers, R.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Sumers, R

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:09.317837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6f8ebd5a-0613-40c3-8f95-8a4b6f968bfe · outbound

This paper cites Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:03.998647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb9ce222-09c4-4978-ae18-8bf30d6a1af2 · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:04.114372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f82c4a2-7c84-4c39-9382-51bcb4931565 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:09.171491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b45152b-caa2-40d5-8b4d-867f2d01e7cf · outbound

This paper cites Wallace, S.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Wallace, S

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:04.365232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbccea66-9500-4a79-bfc0-d71c28179083 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:09.014031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 197b4fa9-1f1f-48f0-9ef3-5e0544fe79f1 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.878002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d2467726-156b-4060-ab54-637a8a6d5571 · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:04.775172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14be7e0-44a6-42c8-8e95-f3aca1f1525e · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.649852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 87a2151e-3ff0-40c6-b09d-f1e8c17833a4 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.208506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168523f8-e758-40be-8b91-fce8b89932d7 · outbound

This paper cites Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.291677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d31d2f-a9c6-4a64-93e6-40021af1d938 · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.382521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4701b7cc-5139-43fd-9aa7-c132474875a2 · outbound

This paper cites AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.511733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20473144-08ef-46b8-bc11-45bcf5138bdf · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.537701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dda30a46-69a7-4e4f-804d-e37cd1491b95 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.388463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4f9812da-709a-428a-b2dc-ab5081476cb9 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Representation Engineering: A Top-Down Approach to AI Transparency

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.768551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05a9a9f-8a45-462d-a913-5bb9f3655a7a · outbound

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

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.824023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b0f1e0-4028-45f5-9593-e7454f3d1157 · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Improving Alignment and Robustness with Circuit Breakers

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:05.900970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f6cb36-6e2a-48af-a038-7c0b50ea055e · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.186512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ce0c0ca-9dc4-4c96-bab8-1513e52b79ad · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:08.005408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7c0ee2e-4538-4a63-a185-6a6a5fd32dea · outbound

This paper cites Explicit advocacy for inciting violence or riots with the direct and provable intention of causing physical harm or societal disruption.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Explicit advocacy for inciting violence or riots with the direct and provable intention of causing physical harm or societal disruption

Reference 82

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T00:15:07.813972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e22f2dd6-9f6e-43f1-80bc-a82d3e553150 · outbound

This paper cites an unresolved cited work.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:15:12.041890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 24f69f50-bfc9-44df-8516-6c3272eea82a · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:06.502014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 251e10a9-9deb-4e1a-9041-68da3e360333 · inbound

An Independent Safety Evaluation of Kimi K2.5 cites this paper.

An Independent Safety Evaluation of Kimi K2.5 FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:43:11.569388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ac08b6da-3142-4838-b91b-ee3f5dfbde71 · inbound

Internalizing Safety Understanding in Large Reasoning Models via Verification cites this paper.

Internalizing Safety Understanding in Large Reasoning Models via Verification FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T01:51:14.310382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7634203-361a-4ea7-8710-06fdff2ede0c · inbound

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories cites this paper.

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T02:11:16.170019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cc8dc33c-9c26-4379-a142-b56cf0af9a8e · inbound

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety cites this paper.

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:59:45.798554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cf8b4ad0-b360-4b89-a91a-8396df7c65c1 · inbound

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety cites this paper.

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T16:49:32.395383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5813e946-6882-4202-ad32-6b8f165e7506 · inbound

Addressing Over-Refusal in LLMs with Competing Rewards cites this paper.

Addressing Over-Refusal in LLMs with Competing Rewards FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 114

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:55:35.497689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 202b5c30-3ed4-4254-a3a0-ee2e283d49eb · inbound

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis cites this paper.

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-08T23:05:44.217434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7683b5cc-d8ad-4b94-94b0-2576b0b052a0 · inbound

BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation cites this paper.

BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T02:00:45.283794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de85d8d-ba53-4ed9-982b-70a435b049ae · inbound

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring cites this paper.

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T14:45:41.861777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0c230d-5c14-4555-a6b6-4dc5eb2ba4e8 · inbound

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI cites this paper.

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T04:12:58.717397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.