Paper Citation Record · LEDGER

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models

As of 22 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 3 inbound Pith citation observations for arXiv:2504.21053.

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

pith.paper-citation-record.v1
2504.21053 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:33:11.895798Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T03:57:57.052252Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T22:31:19.414729Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy1
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 42c2dc98-afb5-43fe-9584-7d52fa3079b1 · outbound

This paper cites URL: " 'urlintro :=.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models URL: " 'urlintro :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.716810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 076c744c-46cf-46b0-9744-5fcfc66b1c5a · outbound

This paper cites write newline.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.724386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347cc208-4f15-4768-8b24-90b690d60797 · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.730582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2fe4983-8c5e-4a8c-a953-c5aadff40d70 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:33:12.476716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e6f07c59-ba5c-4dc5-b3f2-57d72bf1a01c · outbound

This paper cites Chiang, Z.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Chiang, Z

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:33:12.459848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 48eb127e-111a-43bd-827c-0f1b9521e0b2 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.749823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcb31f5c-0917-4cad-a08e-5fbb85964472 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.756846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa6cb716-eb98-4679-b867-6b9074b7c1fb · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.762587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69031f02-918a-410f-85c8-01ce3f08d1d6 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.776085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a6ef4f-f2dc-4c03-9743-c00caac43d70 · outbound

This paper cites Mistral 7B.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Mistral 7B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.782192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ada9f8-ede8-478f-a75f-aeef5ccdc6a5 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.787854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ac35d16-37d2-4ea5-8302-3b79771a2378 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.792894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64fafb6-1742-41cd-abc8-cd146e66c4dd · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.797685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1b1c36-5fe8-4511-bd4c-667aa5f72602 · outbound

This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.803668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2099da-6860-4bfc-8dc0-45fd9335f1ec · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.809302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55208603-d1ca-4c78-b1f7-66c6ff447880 · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.814591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d571d679-be0c-4c99-90df-625a98a6a874 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.819739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f49d09-3b5c-4066-875e-50d81a985c0d · outbound

This paper cites To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.825181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc416fb-f0c7-4594-adab-06930b48ebfd · outbound

This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Evil Geniuses: Delving into the Safety of LLM-based Agents

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.831418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b531d147-0991-469f-91a4-ed6da32878cd · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.836648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eec40907-6d21-4c45-946a-3b556c0aca3f · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Finetuned Language Models Are Zero-Shot Learners

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.842583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b63665b-7c5a-40e5-81a5-57dea9952ae5 · outbound

This paper cites an unresolved cited work.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.849066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9842d1c3-4b93-464b-aded-7334c802a1be · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Low-Resource Languages Jailbreak GPT-4

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.854124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57639e34-162d-43de-a771-01d083497ae9 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.859545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45cb1cb-4d4b-4557-8dae-6afd2da702b0 · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.865614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19faeb0f-9330-440e-bb5c-f0295556c578 · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.871022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1be42727-07c2-4019-9386-f7c37528ff82 · outbound

This paper cites Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.877687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 733aab27-5d09-4e3f-8a73-4d1720e9ffc3 · outbound

This paper cites Don't Say No: Jailbreaking LLM by Suppressing Refusal.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Don't Say No: Jailbreaking LLM by Suppressing Refusal

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.883975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6421b070-d893-495a-8809-42b896282eff · outbound

This paper cites Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.890422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ab447ec-7737-45e9-ba47-142a7673a71f · outbound

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

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.895798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 58744180-127f-4436-9145-3444b7cf8dae · inbound

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring cites this paper.

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models

Reference 19

Resolution: malformed identifier; arxiv_id, observed 2026-05-16T22:31:19.417917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 93ab2728-ee18-44e4-b6c9-379942709885 · inbound

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints cites this paper.

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:21:01.722974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c1e420db-5126-429d-bbdc-2a73b18457bd · inbound

Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks cites this paper.

Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T03:57:57.052252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.