Paper Citation Record · LEDGER

What is in Your Safe Data? Identifying Benign Data that Breaks Safety

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2404.01099.

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

pith.paper-citation-record.v1
2404.01099 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

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

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:36:57.232187Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 2be4a18c-a26e-4618-98b9-899639c55126 · inbound

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey cites this paper.

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-23T20:58:26.203927Z

Source-reported events for the cited work

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

Observation 507c2555-b835-4e2c-9420-2b012ef64f6b · inbound

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration cites this paper.

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:36:57.232187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9306aa5-16ba-4a9d-985a-e15869da3867 · inbound

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems cites this paper.

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:36.525213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1e9c93-716b-47aa-80f4-d8cb31853c12 · inbound

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning cites this paper.

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T19:54:57.757943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca45d46b-9ab3-4090-b410-2d21b055204e · inbound

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning cites this paper.

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:59:55.836898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f60e73e-9d4b-4f49-8e19-b2e696981164 · inbound

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting cites this paper.

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T08:49:32.440280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5a65d4-5b88-4a6d-a088-cfd64eff9bd2 · inbound

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety cites this paper.

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:28:48.692615Z

Source-reported events for the cited work

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

Observation 10113af1-8588-409f-9caa-9fdf7128c5d0 · inbound

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs cites this paper.

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:02:24.884263Z

Source-reported events for the cited work

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

Observation e7872cb9-cad8-4c76-9e00-a6800d138e47 · inbound

Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains cites this paper.

Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:11:19.227998Z

Source-reported events for the cited work

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

Observation d45a7e21-cef3-48ef-b179-cb01ec587cfe · inbound

The Power of Order: Fooling LLMs with Adversarial Table Permutations cites this paper.

The Power of Order: Fooling LLMs with Adversarial Table Permutations What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:36:06.409979Z

Source-reported events for the cited work

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

Observation 492afa69-b123-408a-b40c-0389eae792a3 · inbound

The Power of Order: Fooling LLMs with Adversarial Table Permutations cites this paper.

The Power of Order: Fooling LLMs with Adversarial Table Permutations What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:26:16.600810Z

Source-reported events for the cited work

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

Observation e9c2c0d4-603d-46b3-a41a-da9c662b7e5f · inbound

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning cites this paper.

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:45:44.176489Z

Source-reported events for the cited work

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

Observation aa4457c7-3fc7-4704-86a0-87c8fa73a1b2 · inbound

Why Do Safety Guardrails Degrade Across Languages? cites this paper.

Why Do Safety Guardrails Degrade Across Languages? What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:18:21.047903Z

Source-reported events for the cited work

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

Observation 8350b29d-d1b7-4ca6-a49e-db36f69d00a2 · inbound

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning cites this paper.

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:46:10.215308Z

Source-reported events for the cited work

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

Observation 60817586-e035-49c2-9647-8334b689781a · inbound

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift cites this paper.

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T07:44:09.310328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e96925c6-51e0-4486-8e11-c552925adf0d · inbound

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment cites this paper.

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment What is in Your Safe Data? Identifying Benign Data that Breaks Safety

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T15:28:39.430455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.