Paper Citation Record · LEDGER

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

As of 23 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 3 inbound Pith citation observations for arXiv:2501.14073.

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

pith.paper-citation-record.v1
2501.14073 v2

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T15:26:45.002665Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:33:07.497989Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T14:44:55.118959Z

Reference resolution

55 of 55 outbound references displayed

verified exact0
verified fuzzy0
unresolved55
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e79deb81-c4d4-425e-a182-03c3e41122b1 · outbound

This paper cites GPT-4 Technical Report.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.705756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edaad7cd-25b1-4988-90f7-d09c9d5fd1ea · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.968861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 29f940cf-ea5b-4eb5-9ff6-035bbce956f8 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.951126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ba54841a-cfcf-4f80-92d0-ac92bdffa60a · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.721946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4650de60-f2e4-44ff-ba58-45a2523ecb6b · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.934660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3dd11cb7-2770-420e-bc5c-8fa45bb116b7 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.917476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e98bdbc8-e101-4a3f-b04d-0fc83a2a3989 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.902049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0a954d69-e687-461f-a019-5acf8a5c1f3a · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.885944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 462ba362-ceb9-462c-9aef-af311e3e0027 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.749673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d903e46-d407-4eb3-b567-7302638bb2fa · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Multilingual Jailbreak Challenges in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.755746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afd8d45-dd9e-4c55-bc1e-b3f9c6c1be48 · outbound

This paper cites Toxicity in ChatGPT: Analyzing Persona-assigned Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.761325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539772e5-607e-4778-9bf8-8538fe4a525c · outbound

This paper cites The Llama 3 Herd of Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.766553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94480272-e09c-44b0-b7da-9fe6022ce3e7 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.859327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 449b55f9-84ad-4c13-9e78-eb5288c72385 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.843843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a0d586c-f8b1-4921-8ab3-218ac8518900 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.827044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 191faf10-1bf4-42ed-add2-00d336cfce0b · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.791246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c6074d2-5891-4be2-8b49-4fc6a59d6c8d · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.795996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 378d74ba-fbfc-44cc-a81e-aff3704550fe · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.797994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4a0845f2-baa3-4b2c-9eeb-9907478e090e · outbound

This paper cites Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.806667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c58a4fe0-9b4c-4478-91a6-d1638a2d460a · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.779701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3c133b49-b33b-4b15-8d70-cfa1f086f38f · outbound

This paper cites GPT-4o System Card.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language GPT-4o System Card

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.816636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e8feaa-6cb8-4bcd-845f-1d0f24ecc1ee · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.821622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb3976d-72b8-442e-a8bc-4c4750727bfb · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.761663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b36e5c73-a319-4c6b-a7af-90fc3d8cbad5 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.745082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 222aaf8b-dc86-4da7-b2db-035aa71a7aec · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.837089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54e296c0-deae-42ec-9dd4-476a3b175d00 · outbound

This paper cites Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.842059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607fd7a0-ed71-425d-90c1-346096314bd6 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.847720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ea4937-6540-475b-872e-d78bccc94feb · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.715828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 80e3d4d2-36cb-4865-bd51-6b2d4323419a · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.699383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7cfaba5e-40ae-4134-a4b7-9a071d9e7699 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.862309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6afe979-2142-4d1f-89b2-f9cab9be124e · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.681891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8b184632-d3b3-4e19-b9d6-42a97bec443e · outbound

This paper cites StereoSet: Measuring stereotypical bias in pretrained language models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language StereoSet: Measuring stereotypical bias in pretrained language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.872643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74af5dd0-b8ec-44b1-a527-7e05865cbb59 · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.877975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60096014-cf00-4bea-9a4a-e62085e6d5be · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.884070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48da9f4f-fb8f-4711-a158-8bc611d31050 · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.889820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ad5612f-5f2b-46dc-bac7-3e9bdc78fd2d · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.663777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 38e32446-eb6b-4852-a28a-a68f2f087e26 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.644083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 028f838a-3bdb-40a4-89db-a8c365983619 · outbound

This paper cites Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.905639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d9e8f4f-fe7c-40c1-b8b1-ccf457588de6 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.622993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1d565364-63d5-489e-a877-a6bf50a03be8 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.604322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d58e5258-7d76-4722-bec2-7c184161535a · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Gemini: A Family of Highly Capable Multimodal Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.920901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34bd16ff-426e-4dc2-9ca3-bcca31d08e55 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.585497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 40097a49-5464-4fe3-b99f-25c91ae9998d · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.935866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06dc8f2c-63d4-41b7-afe6-c844e67114d7 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.557778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 76b44438-9997-4a01-bcf7-8315e95f5337 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.946131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61fc65f2-2fe9-40b7-a9c3-0bd9406ef35f · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.530317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1c9b9164-c843-43ed-a9d9-bee30eb3b6b6 · outbound

This paper cites Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.959754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34195a89-002c-4de1-8b08-2cfc602de11c · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.965317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab0e4c58-72b3-43b6-b007-7493783cc313 · outbound

This paper cites Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.970756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4b6d9ad-6eca-4bae-8153-9593de4dbab4 · outbound

This paper cites an unresolved cited work.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-10T15:26:45.512316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d1729677-0533-44d4-922b-4874f4d38f52 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.981699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5411edb4-b80f-47d5-bd06-6375f5e47221 · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.986606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43be8259-9eda-41c8-9c75-b4f0b336f598 · outbound

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

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.991669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4771f75-aa83-4274-895f-325f5aadaf71 · outbound

This paper cites online" 'onlinestring :=.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language online" 'onlinestring :=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.996754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a791645c-4542-4031-9eb7-6294651316de · outbound

This paper cites write newline.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language write newline

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:45.002665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5d77059b-ab7a-4eaf-bb90-026755e62fa9 · inbound

XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration cites this paper.

XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-22T14:44:55.121514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 192fa0f6-a9e8-493e-972d-abd875d5b724 · inbound

Bullying the Machine: How Personas Increase LLM Vulnerability cites this paper.

Bullying the Machine: How Personas Increase LLM Vulnerability LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:33:07.497989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 262679ca-0a82-4d45-8ee3-5f6e6e274c4c · inbound

A Technical Survey of Reinforcement Learning Techniques for Large Language Models cites this paper.

A Technical Survey of Reinforcement Learning Techniques for Large Language Models LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:59:27.404814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.