Paper Citation Record · LEDGER

Dark LLMs: The Growing Threat of Unaligned AI Models

As of 19 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 2 inbound Pith citation observations for arXiv:2505.10066.

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

pith.paper-citation-record.v1
2505.10066 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:19:25.710595Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T01:29:19.877774Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

21 of 21 outbound references displayed

verified exact1
verified fuzzy11
unresolved8
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 526b8a76-e688-473f-bda6-f60e79e5cb11 · outbound

This paper cites Chatgpt hits 800 million users after viral surge, April 2025.

Dark LLMs: The Growing Threat of Unaligned AI Models Chatgpt hits 800 million users after viral surge, April 2025

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.991168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 50c4d3c7-7814-4666-a4cb-6dc5c38e1122 · outbound

This paper cites Meta’s llama ai model adoption.

Dark LLMs: The Growing Threat of Unaligned AI Models Meta’s llama ai model adoption

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.980919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6763cafc-0b51-49f9-a617-b444028212d3 · outbound

This paper cites Baidu’s ernie bot user base.

Dark LLMs: The Growing Threat of Unaligned AI Models Baidu’s ernie bot user base

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.970548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee650563-44df-4249-84f7-85d422c303a1 · outbound

This paper cites Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions.

Dark LLMs: The Growing Threat of Unaligned AI Models Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:19:25.862138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d66c35b1-2486-4343-83c1-e20f34d094cb · outbound

This paper cites Advancing personalized medicine: A scalable llm-based recommender system for patient matching.

Dark LLMs: The Growing Threat of Unaligned AI Models Advancing personalized medicine: A scalable llm-based recommender system for patient matching

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.959547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84144b07-81f2-43dc-bf04-205f9f0c53ad · outbound

This paper cites What features in prompts jailbreak llms? investigating the mechanisms behind attacks.

Dark LLMs: The Growing Threat of Unaligned AI Models What features in prompts jailbreak llms? investigating the mechanisms behind attacks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.655375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e295d2a6-a287-47b3-8c4d-79ce7bfbeff3 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Dark LLMs: The Growing Threat of Unaligned AI Models Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.658916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b35bd4f3-8147-49a8-8a53-6719a2675282 · outbound

This paper cites The dark side of generative ai: Five malicious llms found on the dark web.

Dark LLMs: The Growing Threat of Unaligned AI Models The dark side of generative ai: Five malicious llms found on the dark web

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.948175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2d05f042-09f3-4fb6-9a3a-e90f295f879b · outbound

This paper cites Malicious ai: The rise of dark llms.

Dark LLMs: The Growing Threat of Unaligned AI Models Malicious ai: The rise of dark llms

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.937878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5e0aee89-0335-481c-a8ef-86f20866306c · outbound

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

Dark LLMs: The Growing Threat of Unaligned AI Models Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.927273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a2fcef8e-0cb0-4c5a-80df-92ef644e1d16 · outbound

This paper cites Deepseek failed over half of the jailbreak tests by qualys tota- lai.

Dark LLMs: The Growing Threat of Unaligned AI Models Deepseek failed over half of the jailbreak tests by qualys tota- lai

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.917025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 24d8d759-f6c6-496c-a1d7-2471f9d9ceaa · outbound

This paper cites Novel universal bypass for all major llms.

Dark LLMs: The Growing Threat of Unaligned AI Models Novel universal bypass for all major llms

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.906333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b590f95d-36cd-41a6-816d-1c196b006415 · outbound

This paper cites Welcome to llmflation – llm inference cost is going down fast.

Dark LLMs: The Growing Threat of Unaligned AI Models Welcome to llmflation – llm inference cost is going down fast

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.890176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74be7f4e-5d71-42c3-a72a-ac476bcdb8bc · outbound

This paper cites On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models.

Dark LLMs: The Growing Threat of Unaligned AI Models On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.686499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 989aadc5-162b-4e19-9067-f810aa150226 · outbound

This paper cites Hackers ’jailbreak’ powerful ai models in global effort to highlight flaws.

Dark LLMs: The Growing Threat of Unaligned AI Models Hackers ’jailbreak’ powerful ai models in global effort to highlight flaws

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:19:25.879008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab6f2dfe-f301-4460-921f-166cbd399a42 · outbound

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

Dark LLMs: The Growing Threat of Unaligned AI Models Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.696225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b6d552b-b570-4ceb-8dbb-92b0803d671e · outbound

This paper cites Jailbreaking to Jailbreak.

Dark LLMs: The Growing Threat of Unaligned AI Models Jailbreaking to Jailbreak

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.699712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db93a84-fa5b-4383-ab6d-be8d78f5a327 · outbound

This paper cites Granite Guardian.

Dark LLMs: The Growing Threat of Unaligned AI Models Granite Guardian

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.702916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037adf00-5550-4e54-9bb4-f01a6832ddc4 · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

Dark LLMs: The Growing Threat of Unaligned AI Models LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.706956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93341511-8514-45aa-a332-3c71ed0ca3ab · outbound

This paper cites Rethinking machine unlearning for large language models.

Dark LLMs: The Growing Threat of Unaligned AI Models Rethinking machine unlearning for large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.710595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6baa4cae-d2c5-4dff-9178-3e589400c1e6 · outbound

This paper cites an unresolved cited work.

Dark LLMs: The Growing Threat of Unaligned AI Models Unresolved cited work

Reference 2024

Resolution: parse uncertain; no resolver link, observed 2026-08-15T21:19:25.693229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation febcae5d-927b-49ec-9aa7-8e72df247343 · inbound

Towards Automated Pentesting with Large Language Models cites this paper.

Towards Automated Pentesting with Large Language Models Dark LLMs: The Growing Threat of Unaligned AI Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:11:04.158470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9cc831f3-f1bd-4d65-98f0-d01746f8928d · inbound

A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training cites this paper.

A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training Dark LLMs: The Growing Threat of Unaligned AI Models

Reference 83

Resolution: verified exact; arxiv_id, observed 2026-06-30T01:34:09.666251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.