Paper Citation Record · LEDGER

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak

As of 12 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2412.17522.

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

pith.paper-citation-record.v1
2412.17522 v2

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:31:31.746425Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T04:35:51.583460Z

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

47 of 47 outbound references displayed

verified exact0
verified fuzzy0
unresolved47
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 05eed926-717a-4a11-9f32-31b84cfff728 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.367338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d86034da-2d3c-4d3a-86d2-3a939443e31f · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.552515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78d196db-ad97-49f7-871d-c73f7150d652 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.557406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258167ae-6509-46a5-a8b7-a21c722cad5d · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.562431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbdd6212-9106-47a2-85fd-dbd762144e02 · outbound

This paper cites Plug and Play Language Models: A Simple Approach to Controlled Text Generation.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.567234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8d74daa-42c4-4fdf-a5d3-e7f0ccd4df6b · outbound

This paper cites The Llama 3 Herd of Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.571939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66422da4-9284-4434-adf0-a283237a2e44 · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Attacking Large Language Models with Projected Gradient Descent

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.576750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf966e1-90ab-4a5c-a92e-c23584959e55 · outbound

This paper cites DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.581240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a625f936-e936-46ac-aa9b-eb391abd8c0d · outbound

This paper cites Gradient-based Adversarial Attacks against Text Transformers.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Gradient-based Adversarial Attacks against Text Transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.585911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da67d322-0dc0-48f2-9877-299b2f4e60d8 · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.589895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87a80c1c-6819-4178-863c-700e4be298ea · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.593737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3bd28ae-2b37-46ff-85b3-1c348a424fd6 · outbound

This paper cites DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.597821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc28aa36-56b9-442a-a3b2-78a3b6ede325 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.601771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f2a65b-4279-44a0-961b-73e8828e3f89 · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.605922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f622f5-f28a-4d20-8c9b-2b2922760e8a · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Categorical Reparameterization with Gumbel-Softmax

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.610328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0904a54e-2896-4d2d-9875-522f8232332b · outbound

This paper cites Mistral 7B.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Mistral 7B

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.614678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68185f2f-8481-4f23-bf10-81b2a288b926 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.327797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9142b51b-2d74-46a8-87c2-d5258cd8c6a7 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.313078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b98a1bfc-e124-4bc0-ab30-ffa5a97e37a9 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.297780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 77ae4c2d-05d4-4ae1-aec4-21d7c24972ae · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.631402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53768670-84d1-4730-be5b-172b034e4a1b · outbound

This paper cites Discrete diffusion modeling by estimating the ratios of the data distribution.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Discrete diffusion modeling by estimating the ratios of the data distribution

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.635839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d435254-a92a-4b2e-bf17-e1230535c943 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.273069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ea4e34ad-780a-441c-b28b-86fd8c9742fc · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.644331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f72979ca-8f07-469a-a2e3-dfbd03e41ae3 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.649193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70337389-7629-4802-b532-15ef011f6c38 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.653316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6820cef2-53ea-4c85-bf2e-f59dea371f3f · outbound

This paper cites Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.657432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c9f58f2-c56e-4cdf-873c-0ceb2da7249f · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.661915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fed09a-a740-4dd2-aea9-1d53338de80e · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.666471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dce9e06-85cc-4585-868c-2b24b4433b98 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.670815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6013bc43-a3d9-40b3-b904-79138c4dfd7a · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.232860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ac8622cd-3341-4e7c-8dc7-02b0d9625542 · outbound

This paper cites Harnessing the Plug-and-Play Controller by Prompting.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Harnessing the Plug-and-Play Controller by Prompting

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.678401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fba8892d-4e71-4bd4-8f40-9fa3d6560746 · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Aligning Large Language Models with Human: A Survey

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.682237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4f495d-a951-47e0-9bb6-39d5b07c78c7 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.686323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2554d994-edb1-44ee-bc37-68b81b04d58f · outbound

This paper cites Gradient-Based Language Model Red Teaming.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Gradient-Based Language Model Red Teaming

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.689991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d762d3c-4214-4523-b47c-f83939a6c613 · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.209076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b92edd19-5e98-4337-91f6-107f28fbfbc0 · outbound

This paper cites Jailbreaking as a Reward Misspecification Problem.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Jailbreaking as a Reward Misspecification Problem

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.697628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002b8ce0-ef96-4d78-80de-b2de3873f9af · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:31:32.192862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a5b11e94-ed15-4d34-abee-79438d50a299 · outbound

This paper cites DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.706019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51edbe05-782d-44f1-9cf5-0b0c48e7f1b8 · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.710393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc37adfd-afe1-43ec-b639-b5a76c831ed9 · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.714580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ce9537d-bafe-470d-a4f3-6956a74756c9 · outbound

This paper cites PAWS: Paraphrase Adversaries from Word Scrambling.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak PAWS: Paraphrase Adversaries from Word Scrambling

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.718925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 792fd9b5-499f-4abc-946a-4f9c4d7886a5 · outbound

This paper cites On Prompt-Driven Safeguarding for Large Language Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak On Prompt-Driven Safeguarding for Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.723417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d167eb0-6339-4370-b193-4b6957f5d2b3 · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.727827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d06e451-8927-46e8-8431-35398126ba2c · outbound

This paper cites an unresolved cited work.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.732594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5f40b0-75db-4879-8887-5808a8f13fd3 · outbound

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

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.736732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4edaf3b3-6454-45a2-bb4d-aa914f95184e · outbound

This paper cites online" 'onlinestring :=.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak online" 'onlinestring :=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.741097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c12655af-315a-4027-b665-8530a972e3e1 · outbound

This paper cites write newline.

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak write newline

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:31.746425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2bce4872-3f11-43f0-a1a1-be8949728b2f · inbound

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models cites this paper.

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-06-26T04:38:59.152801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.