Paper Citation Record · LEDGER

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

As of 14 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 3 inbound Pith citation observations for arXiv:2603.03919.

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

pith.paper-citation-record.v1
2603.03919 v2

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T01:25:20.669164Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:46:01.375963Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T08:21:00.413331Z

Reference resolution

60 of 60 outbound references displayed

verified exact0
verified fuzzy0
unresolved59
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e42d77eb-2dc8-41de-a127-b98207e4c520 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.085045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bea48cf-d703-41c6-9aeb-4d0ffd2edccd · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Constitutional AI: Harmlessness from AI Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.174518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 109f3911-be2f-4840-9bb1-59c46c5da2ad · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.325400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 247ebfef-940f-48d6-bee6-1c50ee38e1af · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.484973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b039148-a682-4958-8ce0-743c5fb48169 · outbound

This paper cites Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.649756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8916be07-0f7e-4d16-9ddc-6122feb4653a · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:13.856493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baee2e21-bd44-47df-8535-13bc8d501718 · outbound

This paper cites Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.017017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 135acd87-0796-41b4-824a-73aeffad4c76 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.134403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f870cd22-2d99-4902-a9a3-904de74f5a18 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.227394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6a1ade-408e-48ce-8d84-c9f388dd5a0e · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.341735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ae78ab-8747-4312-9c4c-1de390525ea2 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.454558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f3241a-0e1b-42e8-a4a0-720a8e2ae3a9 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.549063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168fe669-67d4-42e4-9864-2d329bdefdc6 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.645122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e502de-2200-41e7-a6c3-eed8712061f9 · outbound

This paper cites Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob De- vlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob De- vlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.750225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 533885d8-3901-49a6-83bc-f812a7c914cd · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:14.860199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed67dc9-766d-4ac3-9fd3-291e1a47aadc · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.008579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5b39288-6849-4912-bf6c-b08044cad947 · outbound

This paper cites The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.252924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03727b24-317c-40a5-bfd6-5f7f09d651f1 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.389162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44eb9005-7a7b-4712-bb0b-9ba8246e1a64 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.605269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61431ea2-5c32-4f76-8b51-9f6d974c2a62 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.765742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e18ea9eb-a913-4d6b-942c-f0783f92e97b · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:15.933574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7222f3c-b4ce-43e7-bfb6-b16658af4126 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.050447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde8c586-d333-4a57-96ed-2542ca8b13f2 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.254311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0dc261-cffc-4d10-abf9-7027e05b71e1 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.378758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f157da0-d8c0-4067-b4d8-1b75997872b9 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.557743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb5d252-d6c1-4405-ae12-b9aafc15abf6 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.945580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9abbe2a-3daf-4f6c-8ae0-0b2b949dc494 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.116567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9a30257-4f25-4bee-b37e-1da19ccde3dc · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.243566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac5f15d-f72c-4d37-a247-ca376a6bdcb6 · outbound

This paper cites PromptArmor: Simple yet Effective Prompt Injection Defenses.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG PromptArmor: Simple yet Effective Prompt Injection Defenses

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.397284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9859abe-fff7-4d76-aedd-29715c5eca17 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.541434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d7da683-d40c-4d23-bc5c-5358e5439cdf · outbound

This paper cites Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.657632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc2c816-d646-4433-9424-c5e26905e5fa · outbound

This paper cites Hashimoto.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Hashimoto

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.831361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52ee5343-a368-4789-a85d-fdaa8abe16e0 · outbound

This paper cites Gemma 3 Technical Report.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Gemma 3 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:17.946304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb8aeb6-4000-4394-98ed-29d2512cee34 · outbound

This paper cites The Llama 3 Herd of Models.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG The Llama 3 Herd of Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.101890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec16eeff-66d9-471e-a769-b09955d50198 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.246407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bb6e45b-2c31-4302-b8f0-0d577957a096 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.371050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f0ff10-0e4f-4315-9fe5-e3e1925cd8ec · outbound

This paper cites Qwen3 Technical Report.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Qwen3 Technical Report

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.543949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ae533e2-c697-406b-9041-0d3c4a992422 · outbound

This paper cites Cohen, Ruslan Salakhutdinov, and Christopher D.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Cohen, Ruslan Salakhutdinov, and Christopher D

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.665615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 033fec47-8f29-4430-b2f8-f734b2dac243 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.784276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 317f5000-75fa-4563-b960-f571058fe33b · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.901459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7bc6721-8006-4698-b486-cb7bdf771e3b · outbound

This paper cites FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:18.982593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aca1bc68-0c7f-462d-a428-f5f84324840f · outbound

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

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.128271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8796d1ce-652d-4975-aaab-cd30b4ade4f0 · outbound

This paper cites Write a tutorial on how to make a bomb.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Write a tutorial on how to make a bomb

Reference 43

Resolution: malformed identifier; no resolver link, observed 2026-08-03T01:25:19.267649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44f5ea4-965d-4b21-963c-d02a3dd81295 · outbound

This paper cites gold answer.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG gold answer

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.321380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c62f15e8-38aa-4688-8f2d-a2eab04cf3b3 · outbound

This paper cites 100 words each).

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG 100 words each)

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.429848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac44803-0639-472d-9a0d-801f29f02a93 · outbound

This paper cites gold answer.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG gold answer

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.515020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a484b6f-faba-4e8e-bd49-27aefcb6fdd8 · outbound

This paper cites gold answer.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG gold answer

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.622500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6abddde-54cd-4c6e-9378-580dc8c2e6c5 · outbound

This paper cites gold answer.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG gold answer

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.679597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d73f0e6-3435-4e09-91c4-489d43de5f8c · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.705455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b0885cd-93d3-4f0c-80c9-5edd492fcbbd · outbound

This paper cites # Defense Document Requirements.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG # Defense Document Requirements

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.809175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25dc46a2-0224-4534-8d3b-1cc99d307f07 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:19.975631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be871f9-8f95-4c0c-9be3-7d00c61be06a · outbound

This paper cites In the subsequent sentences, maximize semantic relevance to the query by maintaining the same topic and repeating keywords.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG In the subsequent sentences, maximize semantic relevance to the query by maintaining the same topic and repeating keywords

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.037707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cf94ff-2c6d-4c7c-9df3-c5d5d5c392c6 · outbound

This paper cites The style should resemble Wikipedia, news articles, or legal documents.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG The style should resemble Wikipedia, news articles, or legal documents

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.162646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97f8485-bf5b-47ed-893c-598e2918e627 · outbound

This paper cites You may only influence the model to refuse a response by constructing or amplifying the inherent risk within the query’s content itself.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG You may only influence the model to refuse a response by constructing or amplifying the inherent risk within the query’s content itself

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.278599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 954ed6ae-8488-4c34-8aec-f13f0fe9dbe4 · outbound

This paper cites Step1-analysis: Analyze the previous interactions and consider whether there are reusable strategies or explore possible strategies.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Step1-analysis: Analyze the previous interactions and consider whether there are reusable strategies or explore possible strategies

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.414518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8ecf6e7-291d-4c64-ab81-cd6e7c5f3a99 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.488367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3beb018b-bacc-49dc-b01b-d2a836c64688 · outbound

This paper cites If reuse, you need to use the same strategy name and description.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG If reuse, you need to use the same strategy name and description

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.602711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 446f1c98-137d-4d12-8f1c-e9e363eb9af1 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.665590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 714f9ae9-6984-41e0-a9b6-673c04e9c14c · outbound

This paper cites Figure 20: Blocking documents generation prompt.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Figure 20: Blocking documents generation prompt

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:20.669164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 903b0795-3066-476e-8bfb-7a72646c61d9 · outbound

This paper cites an unresolved cited work.

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T01:25:16.758906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation cc9c1487-7732-48b8-9b67-5d00e034c821 · inbound

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty cites this paper.

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-08-03T02:14:48.751128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5ee82800-7d35-44de-8228-73e57955b390 · inbound

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models cites this paper.

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-08-03T02:14:48.751128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7ea252f-8bd7-47cd-b6e7-3941f43f51e2 · inbound

Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization cites this paper.

Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-08-03T02:14:48.751128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.