Paper Citation Record · LEDGER

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents

As of 2 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2604.27143.

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

pith.paper-citation-record.v1
2604.27143 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-07T09:47:52.767727Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-02T06:30:47.504484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:23:23.723022Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact18
verified fuzzy7
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch8

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 70a9c334-bc02-4dea-ab13-96a5cba28a15 · outbound

This paper cites Can LLMs Patch Security Issues?.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Can LLMs Patch Security Issues?

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.731189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 8a395793-b26e-4d6c-b9a1-54d7c905d7de · outbound

This paper cites Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.734590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation a0d324dd-dbdd-4d08-86dc-55956d0994b0 · outbound

This paper cites PentestGPT: An LLM-empowered Automatic Penetration Testing Tool.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.727582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 399ca7cb-8d06-41d7-b4cb-620c9529410c · outbound

This paper cites In: Proceedings of the 37th International Conference on Neural Information Processing Systems.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the 37th International Conference on Neural Information Processing Systems

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.193512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 82e71258-92fd-4cc6-91e6-522f296a6f6a · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 5

Resolution: malformed identifier; doi, observed 2026-05-09T04:15:09.512881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 67847d5e-5d3f-4f29-94b5-8a4216348eb6 · outbound

This paper cites an unresolved cited work.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-27T08:08:49.188714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6f4cdebe-823f-4ae1-83f3-1bf94572aedf · outbound

This paper cites In: First Conference on Language Modeling (2024),https://openreview.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: First Conference on Language Modeling (2024),https://openreview

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.183507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 9d4de5cb-8e23-4ca7-b721-9338d443837b · outbound

This paper cites In: Proceedings of the 31st ACM Joint European Software En- gineering Conference and Symposium on the Foundations of Software Engineer- ing.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the 31st ACM Joint European Software En- gineering Conference and Symposium on the Foundations of Software Engineer- ing

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:09.872338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 52ede07c-137d-4552-911e-491af192f45e · outbound

This paper cites Got Root? A Linux Priv-Esc Benchmark.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Got Root? A Linux Priv-Esc Benchmark

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.710414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6370736d-b6db-42ac-873a-4da35432859a · outbound

This paper cites Llms as hackers: Autonomous linux privilege escalation attacks.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Llms as hackers: Autonomous linux privilege escalation attacks

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.701030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 42f93858-37d9-4e95-8ec9-0b093f85a8a1 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents LoRA: Low-Rank Adaptation of Large Language Models

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T09:41:26.703882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 75d55837-1e2f-40d4-87aa-b4b52fbc3c69 · outbound

This paper cites In: Proceedings of the Workshop on Autonomous Cybersecurity.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the Workshop on Autonomous Cybersecurity

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:09.560893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4b1cb86b-d615-4f9e-98c6-a5cdc301d20a · outbound

This paper cites In: Koyejo, S., Mohamed, S., Agar- wal, A., Belgrave, D., Cho, K., Oh, A.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Koyejo, S., Mohamed, S., Agar- wal, A., Belgrave, D., Cho, K., Oh, A

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.207274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 14e44575-9407-4fb6-be09-a15f04753ac4 · outbound

This paper cites In: Proceedings of the 34th Interna- tional Conference on Neural Information Processing Systems.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the 34th Interna- tional Conference on Neural Information Processing Systems

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.216582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 2050b4c5-4c3a-40a6-a95e-9631a3100c48 · outbound

This paper cites A Survey on Large Language Model Acceleration based on KV Cache Management.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents A Survey on Large Language Model Acceleration based on KV Cache Management

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T09:41:26.724087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 3593c2eb-ef12-4adb-97cb-5d4edd9e512e · outbound

This paper cites Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

Reference 16

Resolution: metadata mismatch; doi, observed 2026-05-09T04:15:09.565555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation a04cfacb-37a6-445f-a4fb-8111ca5871bc · outbound

This paper cites Medicina60(1), 148 (2024).

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Medicina60(1), 148 (2024)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.161583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d1b3a3e2-cdfa-476c-ab54-f7e834c67a7b · outbound

This paper cites an unresolved cited work.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-05-27T08:08:49.211906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 0ea4b306-957b-42ab-afbf-6426416071ab · outbound

This paper cites an unresolved cited work.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-05-27T08:08:49.171866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 02e80e61-6b7d-492e-84ba-40c35a34b58d · outbound

This paper cites CIPHER: Cybersecurity Intelligent Penetration-Testing Helper for Ethical Researcher.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents CIPHER: Cybersecurity Intelligent Penetration-Testing Helper for Ethical Researcher

Reference 20

Resolution: metadata mismatch; doi, observed 2026-05-09T04:15:10.227011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 13af5fe8-7c4d-406b-8ca2-b3a5d1a857cc · outbound

This paper cites Available at SSRN:https://ssrn.com/abstract=4850031or https://dx.doi.org/10.2139/ssrn.4850031(2024), accessed by: 26.3.2025.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Available at SSRN:https://ssrn.com/abstract=4850031or https://dx.doi.org/10.2139/ssrn.4850031(2024), accessed by: 26.3.2025

Reference 21

Resolution: verified exact; doi, observed 2026-05-09T04:15:09.543687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 73f7a6f5-b373-44d7-8fad-9dc5887c43e4 · outbound

This paper cites Expert Systems with Applications 299, 129987 (2026).

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Expert Systems with Applications 299, 129987 (2026)

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:09.572238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation a86ecfc8-7478-4f1b-9851-33bf33f96b24 · outbound

This paper cites Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments

Reference 23

Resolution: metadata mismatch; doi, observed 2026-05-09T04:15:09.527642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation ffe618c4-7b57-4a38-af8a-00589cadb3d4 · outbound

This paper cites IEEE Access13, 38889–38900 (2025).

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents IEEE Access13, 38889–38900 (2025)

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:09.522296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 77f52588-1e32-49ec-b066-580141011cc5 · outbound

This paper cites To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.720469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation dc0c79bb-e731-4652-9dc5-ca6ec24db44b · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Zephyr: Direct Distillation of LM Alignment

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:13:57.632488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6d9d1d40-e9cd-486e-80f7-a774f0c708f5 · outbound

This paper cites A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T04:15:09.581136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 15851b8d-7e0b-4ae9-84f6-743db08c5557 · outbound

This paper cites Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models

Reference 28

Resolution: metadata mismatch; doi, observed 2026-05-09T04:15:10.232210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 02f8f52c-3649-4f47-a610-075918840c7d · outbound

This paper cites In: Proceedings of the 20th ACM Asia Conference on Computer and Communications Security.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the 20th ACM Asia Conference on Computer and Communications Security

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:09.536420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 9f01bec8-ca86-4318-b071-c3e6f4b518c2 · outbound

This paper cites NIPS ’22, Curran Associates Inc., Red Hook, NY, USA (2022).

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents NIPS ’22, Curran Associates Inc., Red Hook, NY, USA (2022)

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.199116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 04180086-b9ef-4d80-979e-265c9fbc8e49 · outbound

This paper cites In: Al-Onaizan, Y., Bansal, M., Chen, Y.N.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Al-Onaizan, Y., Bansal, M., Chen, Y.N

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T08:08:49.166717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4bf60c19-0779-4a03-a9c8-373e9b86464d · outbound

This paper cites https://doi.org/10.18653/v1/2024.emnlp-main.62,https://aclanthology.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents https://doi.org/10.18653/v1/2024.emnlp-main.62,https://aclanthology

Reference 32

Resolution: verified exact; doi, observed 2026-05-09T04:15:09.515801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 7ed9ddc6-e060-4b7b-b89e-66984ade10d7 · outbound

This paper cites AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.713634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4b13ab03-cb7c-4b58-8d6a-2346025e16f6 · outbound

This paper cites A comprehensive study of jailbreak attack versus defense for large language models.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents A comprehensive study of jailbreak attack versus defense for large language models

Reference 34

Resolution: metadata mismatch; doi, observed 2026-05-09T04:15:09.508362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 31660786-c32a-427f-b248-d51089afdef4 · outbound

This paper cites CaseGPT: a case reasoning framework based on language models and retrieval-augmented generation.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents CaseGPT: a case reasoning framework based on language models and retrieval-augmented generation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.707202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 57fff38f-b121-4bbc-af32-90a1e23272d8 · outbound

This paper cites In: Proceedings of the Fourth ACM International Conference on AI in Finance.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents In: Proceedings of the Fourth ACM International Conference on AI in Finance

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:10.217513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation aef6a26a-48ff-4aea-96fc-b58646c04198 · outbound

This paper cites Fine-tuning Large Language Models for Domain-specific Machine Translation.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Fine-tuning Large Language Models for Domain-specific Machine Translation

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-09T04:15:10.247220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Pith citing papers

Observation b68d6a61-a247-4ee9-b998-74ee28a2100d · inbound

The Ethics of Autonomous AI Agents for Offensive Security cites this paper.

The Ethics of Autonomous AI Agents for Offensive Security Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T10:23:23.723022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.