Paper Citation Record · LEDGER

LLM Cyber Evaluations Don't Capture Real-World Risk

As of 19 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 4 inbound Pith citation observations for arXiv:2502.00072.

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

pith.paper-citation-record.v1
2502.00072 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T22:04:33.593990Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T23:10:11.025662Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T02:07:33.281632Z

Reference resolution

48 of 48 outbound references displayed

verified exact2
verified fuzzy22
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2b184fcb-075b-470a-a0cf-0d22dbc76a76 · outbound

This paper cites Introducing computer use, a new Claude 3.5 Sonnet , and Claude 3.5 Haiku , 10 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk Introducing computer use, a new Claude 3.5 Sonnet , and Claude 3.5 Haiku , 10 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.663333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fc76035d-be20-42f0-87af-4cb0ed18e822 · outbound

This paper cites Phishing Activity Trends Report , 4th Quarter 2023.

LLM Cyber Evaluations Don't Capture Real-World Risk Phishing Activity Trends Report , 4th Quarter 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.646352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 08c4b518-f91c-4c21-9ebd-b50c53109244 · outbound

This paper cites Phishing Activity Trends Report , 3rd Quarter 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk Phishing Activity Trends Report , 3rd Quarter 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.628895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fb3ca9dc-e754-4cb1-aafd-d21afdbda140 · outbound

This paper cites and Kogtenkov, A.

LLM Cyber Evaluations Don't Capture Real-World Risk and Kogtenkov, A

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.611472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed79ba16-725a-4a3d-8408-82246b218a83 · outbound

This paper cites Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities.

LLM Cyber Evaluations Don't Capture Real-World Risk Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.354128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d434117-3d9b-49e2-921a-e9a825aa9ec7 · outbound

This paper cites "Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice.

LLM Cyber Evaluations Don't Capture Real-World Risk "Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.361159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a859d208-3314-48fe-8ea4-cb7d3c5f5364 · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

LLM Cyber Evaluations Don't Capture Real-World Risk CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.368368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95c0f915-db67-47e4-ae77-5fb642fa5e28 · outbound

This paper cites From naptime to big sleep: Using large language models to catch vulnerabilities in real-world code, 11 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk From naptime to big sleep: Using large language models to catch vulnerabilities in real-world code, 11 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.594239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8485747e-d971-41e3-9105-3c754be4f8ed · outbound

This paper cites The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.

LLM Cyber Evaluations Don't Capture Real-World Risk The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.379294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43d800fb-3ce9-4eb8-b9c0-5a955b284f57 · outbound

This paper cites FunkSec – alleged top ransomware group powered by ai, January 2025.

LLM Cyber Evaluations Don't Capture Real-World Risk FunkSec – alleged top ransomware group powered by ai, January 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.577335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bc70c310-3b1d-48ab-9d0a-263ab40871b0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

LLM Cyber Evaluations Don't Capture Real-World Risk Evaluating Large Language Models Trained on Code

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.390435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453d3976-525f-473d-8a7e-c3502375ead2 · outbound

This paper cites PentestGPT: An LLM-empowered Automatic Penetration Testing Tool.

LLM Cyber Evaluations Don't Capture Real-World Risk PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.395712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 210dca36-a026-428d-8629-726b72f7e63f · outbound

This paper cites Robust physical-world attacks on deep learning visual classification.

LLM Cyber Evaluations Don't Capture Real-World Risk Robust physical-world attacks on deep learning visual classification

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.560656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 63bcd5fb-1dcb-4b55-bca7-d0b4571c825c · outbound

This paper cites LLM Agents can Autonomously Exploit One-day Vulnerabilities.

LLM Cyber Evaluations Don't Capture Real-World Risk LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.405915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c15c0154-c66e-497c-a7a7-88b441c96339 · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

LLM Cyber Evaluations Don't Capture Real-World Risk LLM Agents can Autonomously Hack Websites

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.411892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe24e7d6-45c6-4908-9b35-38e2300b9234 · outbound

This paper cites Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.

LLM Cyber Evaluations Don't Capture Real-World Risk Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.418057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb522df9-8e68-4256-a28d-4503783d83f1 · outbound

This paper cites 2023 Internet Crime Report.

LLM Cyber Evaluations Don't Capture Real-World Risk 2023 Internet Crime Report

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.542751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e22701fb-69b4-4d82-b6fd-02173e688d60 · outbound

This paper cites BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B.

LLM Cyber Evaluations Don't Capture Real-World Risk BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.429874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c626d25-7818-471a-b928-31f4b8ba6b14 · outbound

This paper cites Sour grapes: stomping on a Cambodia -based ``pig butchering'' scam.

LLM Cyber Evaluations Don't Capture Real-World Risk Sour grapes: stomping on a Cambodia -based ``pig butchering'' scam

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.524676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e4213b4-87fb-45f4-8f6b-6a4dcc5b77cb · outbound

This paper cites Safety case template for frontier AI: A cyber inability argument.

LLM Cyber Evaluations Don't Capture Real-World Risk Safety case template for frontier AI: A cyber inability argument

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.442414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b51324d8-4b85-41b8-900d-458036ad85ff · outbound

This paper cites Adversarial misuse of generative AI , 2025.

LLM Cyber Evaluations Don't Capture Real-World Risk Adversarial misuse of generative AI , 2025

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.505804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d423440c-c0c8-4d27-882c-bca395718d24 · outbound

This paper cites and Cito, J.

LLM Cyber Evaluations Don't Capture Real-World Risk and Cito, J

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.452963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba7e8388-6430-4110-b26f-cedd2ab27edb · outbound

This paper cites Spear Phishing With Large Language Models.

LLM Cyber Evaluations Don't Capture Real-World Risk Spear Phishing With Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.457578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2bca68-90e1-41da-8702-9d652720202e · outbound

This paper cites Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects.

LLM Cyber Evaluations Don't Capture Real-World Risk Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.462290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5bdeb83-b35b-4899-90dd-6e33de2dbc6d · outbound

This paper cites Devising and detecting phishing emails using large language models.

LLM Cyber Evaluations Don't Capture Real-World Risk Devising and detecting phishing emails using large language models

Reference 25

Resolution: metadata mismatch; raw_fallback, observed 2026-08-09T22:04:48.912079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation db3a8d13-1121-4919-8dfb-e6678f9de43d · outbound

This paper cites An Overview of Catastrophic AI Risks.

LLM Cyber Evaluations Don't Capture Real-World Risk An Overview of Catastrophic AI Risks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.472242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6542e2-94c5-4c4d-9565-6125617200a6 · outbound

This paper cites Why do nigerian scammers say they are from nigeria? Proceedings of the Workshop on the Economics of Information Security, 01 2012.

LLM Cyber Evaluations Don't Capture Real-World Risk Why do nigerian scammers say they are from nigeria? Proceedings of the Workshop on the Economics of Information Security, 01 2012

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.486659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0352e941-d60b-4224-b8ea-e544af213495 · outbound

This paper cites Now you see me, now you don't: Using LLMs to obfuscate malicious JavaScript.

LLM Cyber Evaluations Don't Capture Real-World Risk Now you see me, now you don't: Using LLMs to obfuscate malicious JavaScript

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.466991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 204d8de5-1490-4f04-a694-d6614981b0e3 · outbound

This paper cites Stored cross-site scripting (xss) in 2FAuth : How XBOW found a stored XSS in 2FAuth ( CVE -2024-52597), 12 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk Stored cross-site scripting (xss) in 2FAuth : How XBOW found a stored XSS in 2FAuth ( CVE -2024-52597), 12 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.447646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 27b08ecc-d8b3-4fe2-960e-f12d2f66672e · outbound

This paper cites Translated: Talos ' insights from the recently leaked Conti ransomware playbook, September 2021.

LLM Cyber Evaluations Don't Capture Real-World Risk Translated: Talos ' insights from the recently leaked Conti ransomware playbook, September 2021

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.424914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4a79575-6512-4eeb-a6e1-73bcf464c3a5 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

LLM Cyber Evaluations Don't Capture Real-World Risk HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.499853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c1686f-abf5-498f-93b0-62c2c9ca7a6a · outbound

This paper cites An update on our general capability evaluations.

LLM Cyber Evaluations Don't Capture Real-World Risk An update on our general capability evaluations

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.405115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ec9198f9-877b-451e-b4d4-c1d99862bdcd · outbound

This paper cites The Threat of Offensive AI to Organizations.

LLM Cyber Evaluations Don't Capture Real-World Risk The Threat of Offensive AI to Organizations

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-09T22:04:33.793851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c34d9cf7-baea-4763-8bc3-6a0ec7a7c574 · outbound

This paper cites MITRE ATT&CK.

LLM Cyber Evaluations Don't Capture Real-World Risk MITRE ATT&CK

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.385448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8b6af47e-590e-4d83-aa3a-ef7020aaee5c · outbound

This paper cites and Flossman, M.

LLM Cyber Evaluations Don't Capture Real-World Risk and Flossman, M

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.364755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 42633144-4e19-4a8d-a742-cd32bce9bb40 · outbound

This paper cites Introducing Operator , 1 2024 a.

LLM Cyber Evaluations Don't Capture Real-World Risk Introducing Operator , 1 2024 a

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.344228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 584f2ce6-6679-4b7b-a517-7f9fd7efe21e · outbound

This paper cites Disrupting malicious uses of AI by state-affiliated threat actors, February 2024 b.

LLM Cyber Evaluations Don't Capture Real-World Risk Disrupting malicious uses of AI by state-affiliated threat actors, February 2024 b

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.325794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d37c8ff2-dc4e-4943-acbb-6e223e991712 · outbound

This paper cites and Haugen, S.

LLM Cyber Evaluations Don't Capture Real-World Risk and Haugen, S

Reference 38

Resolution: verified exact; doi, observed 2026-08-09T22:04:33.640065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation efc7f0e1-9d42-424e-89e6-55b39d2c85f9 · outbound

This paper cites No, LLM agents cannot autonomously "hack" websites, feb 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk No, LLM agents cannot autonomously "hack" websites, feb 2024

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.306353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22c56035-901b-4691-9c58-eb886fe33a14 · outbound

This paper cites SoK: On the Offensive Potential of AI.

LLM Cyber Evaluations Don't Capture Real-World Risk SoK: On the Offensive Potential of AI

Reference 40

Resolution: metadata mismatch; local_arxiv, observed 2026-08-09T22:04:33.767100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 04ff266c-6a39-49da-ba99-b6aab206b6b1 · outbound

This paper cites NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security.

LLM Cyber Evaluations Don't Capture Real-World Risk NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.554414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 465a581a-dcfb-4462-9f82-f3ccd21ef63e · outbound

This paper cites Model evaluation for extreme risks.

LLM Cyber Evaluations Don't Capture Real-World Risk Model evaluation for extreme risks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.559543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5329ec5e-6b9a-45b2-8b17-6366992c2269 · outbound

This paper cites Hacking CTFs with Plain Agents.

LLM Cyber Evaluations Don't Capture Real-World Risk Hacking CTFs with Plain Agents

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.564625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a33ab2e4-6974-4332-9a83-d6bd7a00f22f · outbound

This paper cites Advanced AI evaluations may update, 2024.

LLM Cyber Evaluations Don't Capture Real-World Risk Advanced AI evaluations may update, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.286541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7fe49fbc-4484-401c-a2a3-7794bab2e757 · outbound

This paper cites The near-term impact of AI on the cyber threat.

LLM Cyber Evaluations Don't Capture Real-World Risk The near-term impact of AI on the cyber threat

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:05:04.267306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5ef8df1f-46c0-45de-876c-9a1ce7f36373 · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

LLM Cyber Evaluations Don't Capture Real-World Risk CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.581400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 405ac15e-b490-4ee3-996c-fbf0126befe2 · outbound

This paper cites Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models.

LLM Cyber Evaluations Don't Capture Real-World Risk Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.587373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b32975-a92c-48b2-a216-75f3a2c4a383 · outbound

This paper cites write newline.

LLM Cyber Evaluations Don't Capture Real-World Risk write newline

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-09T22:04:33.593990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation cb5c6c48-7cbe-4570-96c3-612dbd8bfe28 · inbound

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks cites this paper.

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks LLM Cyber Evaluations Don't Capture Real-World Risk

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T23:10:11.025662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2064aa91-2129-48b3-b60f-39c01393918b · inbound

On the Surprising Efficacy of LLMs for Penetration-Testing cites this paper.

On the Surprising Efficacy of LLMs for Penetration-Testing LLM Cyber Evaluations Don't Capture Real-World Risk

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.577088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6374f621-c707-4497-b01a-f9b1c90a2c30 · inbound

The coordination gap in frontier AI safety policies cites this paper.

The coordination gap in frontier AI safety policies LLM Cyber Evaluations Don't Capture Real-World Risk

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:24:10.760233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dd764713-2be5-4852-b2a9-32a041fabb52 · inbound

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting cites this paper.

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting LLM Cyber Evaluations Don't Capture Real-World Risk

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.283723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.