Paper Citation Record · LEDGER

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2507.06043.

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

pith.paper-citation-record.v1
2507.06043 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:18:47.341663Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T21:08:04.673125Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T21:08:06.388576Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy1
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 20ab7275-4286-4557-9065-dbc99fd0f870 · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.488602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca1a89b-0b75-4bdf-9f69-555eb9834939 · outbound

This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.524938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05791a07-f465-41f7-bb98-f0b59ef38b68 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.645786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de9f5339-3746-4348-96d9-378f28bdd6ab · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.749367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f211f1dd-e80a-4b48-9029-1116493f6a2a · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.849506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 155f482f-eb0c-4b09-930b-c5236f1f9e56 · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:42.941390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9a0a10f-545e-408e-a876-ba2746afa4df · outbound

This paper cites Recent Advances in Attack and Defense Approaches of Large Language Models.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Recent Advances in Attack and Defense Approaches of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:43.023171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2213e70-c872-4395-afc6-7cd63728a498 · outbound

This paper cites DeepSeek-V3 Technical Report.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations DeepSeek-V3 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:43.106007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a459e4-4b2b-4c9f-9f7c-cc657cb21a57 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:43.155123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cbfe8c-bc9c-412d-934d-4bf66a9f80dd · outbound

This paper cites The Llama 3 Herd of Models.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:43.324924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a34fef4-bc96-4448-b0cc-ee6154146cec · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:49.761528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 14825689-1475-4b1b-92ab-944630b02ac0 · outbound

This paper cites Cai, James Wexler, Fernanda B.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Cai, James Wexler, Fernanda B

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:18:49.602687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2baaf5bd-1d05-4f98-852d-db0b98c6f7f7 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:49.424805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ee87e432-a3ea-48b7-8126-f346b8db9b00 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:49.237439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f4e61275-a567-406e-9d36-772ed10f644d · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:49.039356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ffdae9da-ff4b-4453-b3b6-53c2e2961b41 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:44.110225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60fcaa8e-59eb-4e78-9b0e-88e058a1dce9 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 17

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T19:18:48.293208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 92ec32f8-01f8-42ac-9f86-3b9e0d7f35e5 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:44.434891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75817f1-eb76-4a4d-ad33-e6183d1af717 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:48.877206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa26c873-6fc4-4540-aa2b-924dd1d18413 · outbound

This paper cites GPT-4 Technical Report.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations GPT-4 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:44.729046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a67b6306-0fed-4213-9137-12a769f00d0f · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:44.823274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a238d2-a2d6-4640-99b8-806ff726846c · outbound

This paper cites Qwen2.5 Technical Report.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Qwen2.5 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:44.931351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39ceda5e-54fd-49f1-883c-711e3adea093 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.033818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f26780fa-9390-45b8-bf79-0ac77c907ffc · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.148774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b578c107-79d4-4f86-b42f-35891a32855f · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.243985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1715f98-6308-4bfa-a4e3-663672797a83 · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.379143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5284303c-4ce3-43b0-a30c-41b934161202 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations A StrongREJECT for Empty Jailbreaks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.500292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d8f141d-59c6-49ae-ba2b-348faa9e9ffc · outbound

This paper cites Hashimoto.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Hashimoto

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.634496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 758c82ee-0cc8-4b74-a19b-d0aaa8d1712a · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.728426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce1bd3a-1c87-4860-93ae-a6b77a32d2df · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Jailbroken: How Does LLM Safety Training Fail?

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.849258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a191a1b-a55e-4e05-8ab0-ed4870e40c1e · outbound

This paper cites Dai, and Quoc V Le.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Dai, and Quoc V Le

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:45.952671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f7b9bf5-41b1-4bcc-b490-cae65e440cd3 · outbound

This paper cites Ethical and social risks of harm from Language Models.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Ethical and social risks of harm from Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.047757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd2c71f7-cde5-4944-bc27-36a99e3ed40e · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.137678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c38dfd-c68d-406b-834d-8f98bd11a601 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:18:48.613526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2bca0902-16d6-4263-b795-1ee6f7ec13bb · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.295508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84632e61-765a-4cf8-b5b5-9911eab0c50f · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.428000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70640b84-e213-4601-b2c0-aa0b955aa74c · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Low-Resource Languages Jailbreak GPT-4

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.549467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b57c8e-c12e-49b7-a269-950a04fd0d57 · outbound

This paper cites How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.662354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36385948-cc43-4a26-8b82-35896d8f38de · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.786950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a5804c-728e-4412-a414-3aaff9b71d58 · outbound

This paper cites an unresolved cited work.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.864156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f3429be-0dbf-4ac4-8253-5162e656584a · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Representation Engineering: A Top-Down Approach to AI Transparency

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.970519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822a0e55-2997-4ae1-8622-df97a4992f59 · outbound

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:47.094379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86dd1667-75f1-4985-ba75-b247edf29fbc · outbound

This paper cites online" 'onlinestring :=.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations online" 'onlinestring :=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:47.235990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d529b9-ac61-4a1e-8e94-43b2e793f351 · outbound

This paper cites write newline.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations write newline

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:47.341663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7c1330a7-e8ce-46f9-b491-83cbe88844a7 · inbound

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs cites this paper.

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-05T21:08:06.426230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.