Paper Citation Record · LEDGER

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 37 inbound Pith citation observations for arXiv:2402.05162.

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

pith.paper-citation-record.v1
2402.05162 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 37 of 37 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:09:30.214370Z

measured 1 of 1 external citation measurements

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

Source: pith, 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

2
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation cbea1368-0965-4239-a6f7-65a30a5b4428 · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 197

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:47:56.149761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d19ef127-391d-4692-9095-2cebbeb04a3d · 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 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 160

Resolution: verified exact; arxiv_id, observed 2026-05-23T20:58:26.085448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 67c7ab49-d440-4829-ac92-4c419c2a1b82 · inbound

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? cites this paper.

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T10:57:22.935082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f43800fa-7f45-467f-9eed-79540da46314 · inbound

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models cites this paper.

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-12T05:33:18.443220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3597628-016d-4927-98e2-0a3546b160f8 · inbound

RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response cites this paper.

RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T11:51:02.957947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec982510-da81-403d-b937-775830088e3b · inbound

Open Problems in Machine Unlearning for AI Safety cites this paper.

Open Problems in Machine Unlearning for AI Safety Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 139

Resolution: unresolved; no resolver link, observed 2026-08-10T21:24:10.723771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ee5772-0a77-4982-9ca0-9adb1b4979c5 · inbound

On Almost Surely Safe Alignment of Large Language Models at Inference-Time cites this paper.

On Almost Surely Safe Alignment of Large Language Models at Inference-Time Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T16:18:40.645718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdb2e949-cf83-4f26-a872-9c43d77b03bf · inbound

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers cites this paper.

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T21:55:56.884625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fa0df6f-d9eb-48c7-a830-30ddec005595 · inbound

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation cites this paper.

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T12:25:30.669881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7200a08c-27e5-4891-a564-699913e1474f · inbound

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies cites this paper.

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T11:42:07.679330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 737f3945-a6cc-4a1f-b817-56b3c983d795 · inbound

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions cites this paper.

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T23:08:02.378812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83cee028-943d-4118-8b61-a51410ccfa8f · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:37:15.996646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a05ecda7-04b6-42b0-a71c-0096387892ab · inbound

Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking cites this paper.

Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:40.675703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b74d362-e9c5-440d-a002-3e225ae1418b · inbound

SoK: Machine Unlearning for Large Language Models cites this paper.

SoK: Machine Unlearning for Large Language Models Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-07T04:59:00.309903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1417b31e-acf9-4e0d-8e52-d63cb862f27c · inbound

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs cites this paper.

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T19:09:30.214370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52b27ab-0ec8-40c8-8109-dde23d632199 · inbound

Linearly Decoding Refused Knowledge in Aligned Language Models cites this paper.

Linearly Decoding Refused Knowledge in Aligned Language Models Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.011420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f295d79-792d-48c6-b9de-c9f683ddced6 · inbound

SDD: Self-Degraded Defense against Malicious Fine-tuning cites this paper.

SDD: Self-Degraded Defense against Malicious Fine-tuning Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.008458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7567ac52-f1d8-4b55-91f0-4a4fd39dcca1 · inbound

S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner cites this paper.

S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T18:12:36.334354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83bd386f-8001-44d2-b4cf-dc27d23048cc · inbound

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection cites this paper.

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T14:57:12.939155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c2c6bea-7436-4b5f-9ab6-3ead28b1ec1b · inbound

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint cites this paper.

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:10:21.164769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4014d4f8-ebe4-4157-9e85-317ab0948343 · inbound

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2 cites this paper.

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T18:58:18.996512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff754a30-a656-4eb2-95b8-cea41a614f96 · inbound

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment cites this paper.

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:35.061007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c81941-8b7a-49bc-b0c1-c2975aaff959 · inbound

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing cites this paper.

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:17:36.571809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 14bad936-292e-4a84-afaa-3747711aabec · inbound

Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression cites this paper.

Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:18:01.269418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e1abcea7-6b34-4377-a29a-6c4741cb95eb · 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 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:21:01.737881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39072647-bc4b-4d17-afb2-9e152a01511a · inbound

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

Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:11:19.355933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7f3f0f3a-43c0-4b6b-8a7f-b6bd7a3dd9a8 · inbound

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models cites this paper.

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T01:46:14.385976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 535a40d2-b828-4c34-90dd-52b3f3e81075 · inbound

Persona-Model Collapse in Emergent Misalignment cites this paper.

Persona-Model Collapse in Emergent Misalignment Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:47:58.787885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 49544792-b9a8-4f1d-bd8d-480e17de09ce · inbound

Persona-Model Collapse in Emergent Misalignment cites this paper.

Persona-Model Collapse in Emergent Misalignment Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:15:47.607612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ab30518a-aa99-46d5-83eb-2fcf73a70a86 · inbound

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling cites this paper.

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:08:11.097483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2c8cc1d3-9a0c-4721-8b48-3d86c6f18b52 · inbound

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak cites this paper.

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T06:19:41.940745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b719db5-9a7a-4486-8ebb-3a322659aa89 · inbound

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving cites this paper.

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:03:47.824267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9459fa0c-106d-4060-b66d-bd0e2592c9f4 · inbound

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets cites this paper.

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:48:32.485913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4669ea2f-2c5e-4dd1-a35e-4804a3b3a840 · inbound

Faithfulness to Refusal: A Causal Audit of Neuron Selectors cites this paper.

Faithfulness to Refusal: A Causal Audit of Neuron Selectors Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-07T15:43:53.891301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bcc8117c-adf3-4adc-a3af-4b28f7f06d9f · inbound

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge cites this paper.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.933979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4088ce3-657f-4ac1-a4de-4894f73b47d5 · inbound

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning cites this paper.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.773439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4dee33-b099-436b-821c-ee82e644ba1c · inbound

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs cites this paper.

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T04:46:15.991367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.