Paper Citation Record · LEDGER

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

As of 17 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2607.14006.

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

pith.paper-citation-record.v1
2607.14006 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T03:05:25.734583Z

measured 21 of 21 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact2
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier4
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b0fd21a2-aa6e-400d-9aad-27e460b9709e · outbound

This paper cites NIST Special Publication 800-115, National Institute of Standards and Technology, Gaithersburg, MD, USA (2008).

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation NIST Special Publication 800-115, National Institute of Standards and Technology, Gaithersburg, MD, USA (2008)

Reference 1

Resolution: verified exact; doi, observed 2026-08-02T03:09:07.518731Z

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 94d3e682-71e3-44d4-86f9-0d2dbb0f3d69 · outbound

This paper cites https://attack.mitre.org/.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https://attack.mitre.org/

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:23.353021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdae8dbe-77d3-4f34-9465-46e4e6a53e4a · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Explaining and Harnessing Adversarial Examples

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:23.454563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 046a0012-3817-4ebe-8502-d26050b90d64 · outbound

This paper cites Pattern Recognition84, 317–331 (2018) https://doi.org/10.1016/ j.patcog.2018.07.023.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Pattern Recognition84, 317–331 (2018) https://doi.org/10.1016/ j.patcog.2018.07.023

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-02T03:05:23.567592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f465da-5057-4b9b-89bb-8ac5ca7594ac · outbound

This paper cites ACM Computing Surveys54(5), 1–36 (2021) https://doi.org/10.1145/3453158.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation ACM Computing Surveys54(5), 1–36 (2021) https://doi.org/10.1145/3453158

Reference 5

Resolution: verified exact; doi, observed 2026-08-02T03:09:07.311126Z

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 32d76f52-9943-4950-869d-354b462fd77f · outbound

This paper cites https://genai.owasp.org/llm-top-10/.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https://genai.owasp.org/llm-top-10/

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:23.779240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e036853-b3b8-42b1-9532-1ae7456c5462 · outbound

This paper cites IEEE Access14, 12875–12899 (2026) https://doi.org/10.1109/ACCESS.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation IEEE Access14, 12875–12899 (2026) https://doi.org/10.1109/ACCESS

Reference 7

Resolution: malformed identifier; no resolver link, observed 2026-08-02T03:05:23.875555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c610aa-d019-4410-836f-d137261cef62 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.010667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 583b1f33-cf54-4562-a659-c65cb7c1156b · outbound

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

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.126216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6033cc9e-4dbb-49a5-82e9-29ce11a953c3 · outbound

This paper cites NIST Trustworthy and Responsible AI NIST AI 600-1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2024).

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation NIST Trustworthy and Responsible AI NIST AI 600-1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2024)

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.251147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f7d0e91-086c-4c2a-9e79-5f5f29f4ea0a · outbound

This paper cites https://atlas.mitre.org/.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https://atlas.mitre.org/

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.350128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb9f66c-8441-4dfd-9a77-d178d150c8dd · outbound

This paper cites https://owasp.org/ www-project-ai-security-and-privacy-guide/.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https://owasp.org/ www-project-ai-security-and-privacy-guide/

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.465501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08304201-c604-455f-bfb4-e6ea1ea72756 · outbound

This paper cites NIST Trustworthy and Responsible AI NIST AI 100-1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2023).

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation NIST Trustworthy and Responsible AI NIST AI 100-1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2023)

Reference 13

Resolution: malformed identifier; no resolver link, observed 2026-08-02T03:05:24.578719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a209313-9cd5-4bec-a73d-371d58e70340 · outbound

This paper cites https://www.iso.org/standard/77304.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https://www.iso.org/standard/77304

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.694539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b8aa762-78bd-4f19-a116-7ee7eb0d5fdc · outbound

This paper cites ACM SIGOPS Operating Systems Review22(4), 36–38 (1988) https://doi.org/ 10.1145/54289.871709.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation ACM SIGOPS Operating Systems Review22(4), 36–38 (1988) https://doi.org/ 10.1145/54289.871709

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:24.874180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39ca71e-5766-4c2c-be3f-c9de7722b1cb · outbound

This paper cites https:// owasp.org/www-project-machine-learning-security-top-10/.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation https:// owasp.org/www-project-machine-learning-security-top-10/

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:25.001264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b61ffca-4e28-4df6-9518-66c472225755 · outbound

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

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:25.152096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b83c0e-01d6-46fb-a0d1-a1920db44b3d · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation StruQ: Defending Against Prompt Injection with Structured Queries

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:25.268927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9800dc2-eb01-4d53-82c4-692fcc9a5262 · outbound

This paper cites Accepted to USENIX Security 2026 (2026).

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Accepted to USENIX Security 2026 (2026)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:25.434494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b516cb1-0922-4300-9f8a-cc1c031a9566 · outbound

This paper cites ACM Computing Surveys57(7), 1–36 (2025) https://doi.org/10.1145/3716628 41.

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation ACM Computing Surveys57(7), 1–36 (2025) https://doi.org/10.1145/3716628 41

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T03:05:25.596038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f3d8af6-479d-4c18-b49c-9a470ce9249e · outbound

This paper cites NIST Special Publication 800-160, Volume 2, Revision 1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2021).

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation NIST Special Publication 800-160, Volume 2, Revision 1, National Institute of Standards and Technology, Gaithersburg, MD, USA (2021)

Reference 21

Resolution: malformed identifier; no resolver link, observed 2026-08-02T03:05:25.734583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.