Security and Privacy in Agentic AI: Grand Challenges and Future Directions | Paper Citation Record

Observation 536244eb-cdb7-473a-8e8f-c74eb1b08923 · outbound

This paper cites Introducing chatgpt,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Introducing chatgpt,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.308425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6960d47-eef6-40b0-b49d-586fad1c6f75 · outbound

This paper cites Privacy perceptions of custom gpts by users and creators,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacy perceptions of custom gpts by users and creators,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.399680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab7536e-06e7-4814-8201-9d892260ccea · outbound

This paper cites Openclaw — personal ai assistant,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Openclaw — personal ai assistant,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.485263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398ee8e5-f540-42a3-ab60-cffe0f30b7cc · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Formalizing and benchmarking prompt injection attacks and defenses,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.604737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 272dbafa-e30b-45c6-b97b-cd0103d94c07 · outbound

This paper cites Gptracker: A large- scale measurement of misused gpts,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Gptracker: A large- scale measurement of misused gpts,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.693205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9be00c8-5378-448e-8b30-f12fbf3da440 · outbound

This paper cites Malicious {LLM-Based}conversational{AI}makes users reveal personal information,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Malicious {LLM-Based}conversational{AI}makes users reveal personal information,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.835931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2d6ce3-49a2-4234-aeea-8dadfd71b763 · outbound

This paper cites On concepts and methods in horizon scanning: Lessons from initiating policy dialogues on emerging issues,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions On concepts and methods in horizon scanning: Lessons from initiating policy dialogues on emerging issues,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:12.973746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ddcf6bb-654a-4087-a7d4-3bd09fe3acfb · outbound

This paper cites Using affinity diagrams to evaluate interactive proto- types,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Using affinity diagrams to evaluate interactive proto- types,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.114549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab3fc126-e461-4067-bf7a-a42faa9f05d8 · outbound

This paper cites Regulatory challenges of robotics: some guidelines for addressing legal and ethical issues,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Regulatory challenges of robotics: some guidelines for addressing legal and ethical issues,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.229979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65ee07b-a66e-4102-834a-18a212de079d · outbound

This paper cites Find the gap: Ai, responsible agency and vulnerability,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Find the gap: Ai, responsible agency and vulnerability,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.351288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62425ab5-94a9-488f-a7c3-7744f6b461d7 · outbound

This paper cites Harms from increasingly agentic algorithmic systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Harms from increasingly agentic algorithmic systems,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.484541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eabb3059-cac0-4107-8230-a2eeccd8b7c4 · outbound

This paper cites General data protection regulation,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions General data protection regulation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.571390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23336480-951f-4e21-8dd0-458a6b164663 · outbound

This paper cites Artificial Intelligence Act,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Artificial Intelligence Act,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.694752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550f8f84-20d5-482a-a508-a78e3bed7dfb · outbound

This paper cites Charter of fundamental rights of the european union,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Charter of fundamental rights of the european union,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:13.854753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203e0c67-3b3f-4543-b3e5-c66d23fa0b6c · outbound

This paper cites An objective metric for explainable AI: How and why to estimate the degree of explainability,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions An objective metric for explainable AI: How and why to estimate the degree of explainability,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.033832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 405dcb28-cd6e-415a-8550-2e50e80e29f6 · outbound

This paper cites Legal XAI: A systematic review and interdisciplinary mapping of XAI and EU law, towards a research agenda for legally responsible AI,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Legal XAI: A systematic review and interdisciplinary mapping of XAI and EU law, towards a research agenda for legally responsible AI,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.146897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e1ab6a-b89c-4346-b596-d795d72d5892 · outbound

This paper cites Understanding accountability in algorithmic supply chains,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Understanding accountability in algorithmic supply chains,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.262708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf310ac-917f-4e73-9533-743abd092fa5 · outbound

This paper cites Ai agents under eu law,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Ai agents under eu law,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.372477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d8882f-e671-4223-bea5-15b14d184ff2 · outbound

This paper cites Digital services act,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Digital services act,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.519442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db074f39-d769-40c0-be2e-363016d3f58d · outbound

This paper cites Medical device regulation,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Medical device regulation,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.614384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d9321f-c799-47a3-8fc1-8326fd18ef35 · outbound

This paper cites Product liability directive,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Product liability directive,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.784154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b65430b-0001-4003-b7d3-a1ff72f12461 · outbound

This paper cites On the quest for effectiveness in human oversight: Interdisciplinary perspectives,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions On the quest for effectiveness in human oversight: Interdisciplinary perspectives,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.954752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dec2c73-6c5d-417f-8dc7-54a74dfdf11f · outbound

This paper cites Fostering appropriate reliance on large language models: The role of explanations, sources, and inconsistencies,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Fostering appropriate reliance on large language models: The role of explanations, sources, and inconsistencies,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.017835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41687e65-cb54-4bf0-8347-ecdfbf8dd90f · outbound

This paper cites Available: https://eur-lex.europa.eu/eli/dir/ 2024/2853/oj.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Available: https://eur-lex.europa.eu/eli/dir/ 2024/2853/oj

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.875837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b22d94ca-d792-4a84-a0ad-e8b586e4e0f8 · outbound

This paper cites Software documentation issues unveiled,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Software documentation issues unveiled,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.271343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af1045dd-a08a-4245-840f-6d3d4a5fffaf · outbound

This paper cites Detecting outdated code el- ement references in software repository documentation,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Detecting outdated code el- ement references in software repository documentation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.398837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f181a372-973d-40e2-8326-d9b26c9ee709 · outbound

This paper cites Software documentation: The practitioners’ perspective,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Software documentation: The practitioners’ perspective,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.123911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca12bbf5-cbe5-4d77-a350-a2219aaa3b46 · outbound

This paper cites Simplifying software compliance: AI technologies in drafting technical docu- mentation for the AI Act,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Simplifying software compliance: AI technologies in drafting technical docu- mentation for the AI Act,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.642583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc0f3e7-e6b0-420a-8fdf-05fc12cbfe89 · outbound

This paper cites Outlining traceability: A principle for operationalizing accountability in computing systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Outlining traceability: A principle for operationalizing accountability in computing systems,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.763285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b65a15c8-c4d6-4759-a4e9-ee6b55139bb8 · outbound

This paper cites An empirical study on compliance with ranking transparency in the software documenta- tion of EU online platforms,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions An empirical study on compliance with ranking transparency in the software documenta- tion of EU online platforms,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.521601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce2f539-45cb-4898-bb5f-7b8f08bec32b · outbound

This paper cites Audit trails for accountability in large language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Audit trails for accountability in large language models,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.987520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ca57d03-d778-4dfa-bd5a-f3730ea9a247 · outbound

This paper cites Regulation (eu) 2024/1689 laying down harmonised rules on artificial intelligence,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Regulation (eu) 2024/1689 laying down harmonised rules on artificial intelligence,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.155077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e16cd78-1a3c-4500-be1e-876e9a71745f · outbound

This paper cites Closing the ai accountability gap: Defining an end-to-end framework for internal algorithmic auditing,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Closing the ai accountability gap: Defining an end-to-end framework for internal algorithmic auditing,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:15.872037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a9ac485-9564-4f90-b536-e878be52dce4 · outbound

This paper cites Regulation (eu) 2016/679: General data protection regulation,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Regulation (eu) 2016/679: General data protection regulation,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.456976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc9e2af-bfbb-4573-9bb1-5bf445ef6cbd · outbound

This paper cites Regulation (eu) 2016/679: Article 32, security of pro- cessing,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Regulation (eu) 2016/679: Article 32, security of pro- cessing,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.537057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04b95f5-c766-4703-b56d-e3fb2d34347e · outbound

This paper cites Accountability capture: How record-keeping to support ai trans- parency and accountability (re)shapes algorithmic oversight,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Accountability capture: How record-keeping to support ai trans- parency and accountability (re)shapes algorithmic oversight,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.324250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 467d02a4-8ea7-4681-a953-d72d65ce0f08 · outbound

This paper cites On cryptographic mechanisms for the selective dis- closure of verifiable credentials,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions On cryptographic mechanisms for the selective dis- closure of verifiable credentials,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.711739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff454e39-92d6-4c71-bf55-7725babb7fd9 · outbound

This paper cites Role-based access controls,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Role-based access controls,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.829885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c8ff70-6bd3-44c3-a85a-a93eb775438c · outbound

This paper cites Harpocrates: Privacy-preserving and immutable audit log for sensitive data operations,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Harpocrates: Privacy-preserving and immutable audit log for sensitive data operations,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.593773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b471ea-de94-41ff-9e3a-d3cfe296c92c · outbound

This paper cites Cognitive bias in decision-making with llms,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Cognitive bias in decision-making with llms,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.211278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f3b7e4-dcae-486a-9333-7845c606fcbe · outbound

This paper cites Towards understanding sycophancy in language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Towards understanding sycophancy in language models,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.314480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3352ce30-620b-464a-881c-36947d597a9f · outbound

This paper cites Agentharm: A bench- mark for measuring harmfulness of llm agents,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Agentharm: A bench- mark for measuring harmfulness of llm agents,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.415025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3441e8ee-0131-4016-a4bc-8ebd2528d221 · outbound

This paper cites A framework for understanding sources of harm throughout the machine learning life cycle,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions A framework for understanding sources of harm throughout the machine learning life cycle,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.077587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de386fe8-8204-445c-bdcc-2a77af6ddd9e · outbound

This paper cites Is general-purpose ai reasoning sensitive to data- induced cognitive biases? dynamic benchmarking on typical soft- ware engineering dilemmas,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Is general-purpose ai reasoning sensitive to data- induced cognitive biases? dynamic benchmarking on typical soft- ware engineering dilemmas,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.553539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6199d998-5ed0-4e00-9848-bd8f951c6adf · outbound

This paper cites Large language models for in-file vulnerability localization can be “lost in the end.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Large language models for in-file vulnerability localization can be “lost in the end

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.626859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bd15b13-0056-4abe-8cd5-af76c2810de9 · outbound

This paper cites Shostack,Threat Modeling: Designing for Security.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Shostack,Threat Modeling: Designing for Security

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.704714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d18f928-3ffb-4d16-9ada-d424d8fac82d · outbound

This paper cites Mitigating prompt- induced cognitive biases in general-purpose ai for software engi- neering,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Mitigating prompt- induced cognitive biases in general-purpose ai for software engi- neering,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.473543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac3788e-e469-44e7-be95-2e0a06db136f · outbound

This paper cites STPA handbook,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions STPA handbook,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.932285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f8d566-30ca-41cf-a9c1-58bcc6b41c90 · outbound

This paper cites Huang and C.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Huang and C

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.987733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72696e31-3c3f-4342-98ba-bdadfa0313da · outbound

This paper cites Multi-agent risks from advanced AI,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Multi-agent risks from advanced AI,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.042868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 043e1671-a520-4499-aa05-90988dfbddc6 · outbound

This paper cites Artificial intelligence risk management framework (AI RMF 1.0),.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Artificial intelligence risk management framework (AI RMF 1.0),

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:17.812590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfdf76f2-d13a-44c3-8a2e-264041247105 · outbound

This paper cites m&m’s: A benchmark to evaluate tool-use for multi-step multi-modal tasks,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions m&m’s: A benchmark to evaluate tool-use for multi-step multi-modal tasks,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.165974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e180c359-834c-4793-889e-2b8c12a00522 · outbound

This paper cites Are more LLM calls all you need? towards the scaling properties of compound AI systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Are more LLM calls all you need? towards the scaling properties of compound AI systems,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.206661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f2b3305-5867-423d-9ef4-146ad22cc329 · outbound

This paper cites Facilitating threat modeling by leveraging large language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Facilitating threat modeling by leveraging large language models,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.318130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff73adf-5d6e-4411-8889-7263f67eb66e · outbound

This paper cites Why do multi-agent LLM systems fail?.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Why do multi-agent LLM systems fail?

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.104817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feb12240-63e9-48a7-bf89-e27996a50d7a · outbound

This paper cites Dignum,Responsible Artificial Intelligence: How to Develop and Use AI in a Responsible Way.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Dignum,Responsible Artificial Intelligence: How to Develop and Use AI in a Responsible Way

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.660546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9be8cad-3590-484a-8f27-bba12908f724 · outbound

This paper cites What to account for when accounting for algo- rithms: A systematic literature review on algorithmic accountabil- ity,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions What to account for when accounting for algo- rithms: A systematic literature review on algorithmic accountabil- ity,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.753616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22295832-3b63-4079-a5d8-f7112698cf70 · outbound

This paper cites Accountability in multi-agent organizations: From conceptual design to agent programming,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Accountability in multi-agent organizations: From conceptual design to agent programming,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.849780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38289ff6-9814-440c-b050-64960fe69758 · outbound

This paper cites Available: https://www.ndss-symposium.org/ wp-content/uploads/aiscc2024-16-paper.pdf.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Available: https://www.ndss-symposium.org/ wp-content/uploads/aiscc2024-16-paper.pdf

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.411345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 760c8a86-52e7-4124-aba8-a943adb5f665 · outbound

This paper cites Measuring progress on scalable oversight for large language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Measuring progress on scalable oversight for large language models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.562275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0859889-9bba-46aa-9a11-dd160e8f5e1e · outbound

This paper cites Value sensitive design and information systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Value sensitive design and information systems,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.196003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36746abd-d58b-49f0-b481-007cddcdffda · outbound

This paper cites Fairness and abstraction in sociotechnical systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Fairness and abstraction in sociotechnical systems,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.277582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f26b29-3572-4dda-809e-723ef582f124 · outbound

This paper cites Inherent trade- offs in the fair determination of risk scores,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Inherent trade- offs in the fair determination of risk scores,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.337789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a8f55c-385f-4d8c-abcc-93d659905f82 · outbound

This paper cites AI safety via debate,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions AI safety via debate,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:18.978283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8244c8de-9e37-4be6-a4c7-7f80fe5449f8 · outbound

This paper cites Improving factuality and reasoning in language models through multiagent debate,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Improving factuality and reasoning in language models through multiagent debate,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.121973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d88dae-0f8e-400a-aa7a-594c6798c801 · outbound

This paper cites Training language models to follow instructions with human feedback,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Training language models to follow instructions with human feedback,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.549819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18613d3f-316d-4d40-8fd5-bf51dde7565f · outbound

This paper cites Constitutional AI: Harmlessness from AI feedback,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Constitutional AI: Harmlessness from AI feedback,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.617858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29fe983d-2a27-4c80-b882-0d8b662b9cfe · outbound

This paper cites Jailbroken: How does LLM safety training fail?.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Jailbroken: How does LLM safety training fail?

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.700510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c0346f-9691-4222-a6d6-19b6b3942c1b · outbound

This paper cites Big data’s disparate impact,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Big data’s disparate impact,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.399420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12125bf0-9dba-4b1c-ab41-c065a9431b27 · outbound

This paper cites The (im) possibility of fairness: Different value systems require differ- ent mechanisms for fair decision making,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions The (im) possibility of fairness: Different value systems require differ- ent mechanisms for fair decision making,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.472889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186c8815-66fc-478e-88b0-639feb8be2fc · outbound

This paper cites Can global XAI methods reveal injected behaviours in LLMs? SHAP vs. rule extraction vs. RuleSHAP,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Can global XAI methods reveal injected behaviours in LLMs? SHAP vs. rule extraction vs. RuleSHAP,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.946162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4bcb82b-e078-424b-ae4d-a33e0e6ea02c · outbound

This paper cites Neuron-anchored rule extraction for large language models via contrastive hierarchi- cal ablation,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Neuron-anchored rule extraction for large language models via contrastive hierarchi- cal ablation,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.028400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23c0a405-f6aa-4770-8849-a12577b99846 · outbound

This paper cites Illocutionary explanation planning for source-faithful explanations in retrieval-augmented language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Illocutionary explanation planning for source-faithful explanations in retrieval-augmented language models,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.069184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f93e56b-6b6e-4e99-8c92-32565b33655f · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Universal and transferable adversarial attacks on aligned language models,

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.791715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a637056e-ba5e-4776-8a8e-a1b95a6077f0 · outbound

This paper cites Small Language Models are the Future of Agentic AI.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Small Language Models are the Future of Agentic AI

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:19.868406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7e22035-521d-40ad-8367-8712839b64e3 · outbound

This paper cites Large language mod- els can strategically deceive their users when put under pressure,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Large language mod- els can strategically deceive their users when put under pressure,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.273319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6099b3-4fe6-4b59-9e60-6dcfc3621a77 · outbound

This paper cites Sleeper agents: Training deceptive LLMs that per- sist through safety training,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Sleeper agents: Training deceptive LLMs that per- sist through safety training,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.330630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3829fb4-3eb6-497c-9cfa-4d4d59ac38d4 · outbound

This paper cites AI, big data, and the future of consent,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions AI, big data, and the future of consent,

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.398914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c80b1ea8-a28a-40cc-89e4-2f6e072aba74 · outbound

This paper cites Assessing model-agnostic XAI methods against EU AI Act explainability requirements,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Assessing model-agnostic XAI methods against EU AI Act explainability requirements,

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.101639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f5b34a-e9e3-4cd1-b5d1-5f9869603ffe · outbound

This paper cites AI deception: A survey of examples, risks, and potential solu- tions,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions AI deception: A survey of examples, risks, and potential solu- tions,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.191433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6844195f-58d0-416d-bbe4-653e87155d12 · outbound

This paper cites Elvira: An explainable agent for value and utility-driven multiuser privacy,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Elvira: An explainable agent for value and utility-driven multiuser privacy,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.638201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19ac1045-fbc7-4286-b3f1-32c57416e6ba · outbound

This paper cites “I know even if you don’t tell me.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions “I know even if you don’t tell me

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.799690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde9afb6-aa25-40d8-8b3c-98c4c2c2ac05 · outbound

This paper cites A survey of privacy in multi-agent systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions A survey of privacy in multi-agent systems,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.901032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8a97923-3195-4913-bbe5-d63671ae1719 · outbound

This paper cites AgentSCOPE: Evaluating contextual privacy across agentic workflows,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions AgentSCOPE: Evaluating contextual privacy across agentic workflows,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.480729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4f56df3-a999-45a0-922b-8f3465311fec · outbound

This paper cites Privacy-enhanced personal assistants based on dialogues and case similarity,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacy-enhanced personal assistants based on dialogues and case similarity,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:20.532620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e805f6a-cb7b-452f-9265-c0363461dad6 · outbound

This paper cites Privacylens: Evaluating privacy norm awareness of language models in action,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacylens: Evaluating privacy norm awareness of language models in action,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.179705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 695cbb69-15e8-42e6-aa6f-41a3392e90fb · outbound

This paper cites Agentic ai: Autonomous intelligence for complex goals—a comprehensive survey,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Agentic ai: Autonomous intelligence for complex goals—a comprehensive survey,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.268615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 282fd760-a4f0-482d-bc88-29e8612d1872 · outbound

This paper cites Large language models must be taught to know what they don’t know,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Large language models must be taught to know what they don’t know,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.374044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a70a58e1-41b4-48f9-bb9b-a86eff3c43d4 · outbound

This paper cites Privacy and autonomous systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacy and autonomous systems,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.011060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1677f068-2ec1-4d0f-b821-34485a603785 · outbound

This paper cites Privacy as contextual integrity,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacy as contextual integrity,

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.081564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db9783a-9eab-4224-823a-453a0435baeb · outbound

This paper cites Intersectional experiences of unfair treatment caused by automated computational systems,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Intersectional experiences of unfair treatment caused by automated computational systems,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.682365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc55a6b3-3d2f-4923-93df-8bf2214fa648 · outbound

This paper cites Bias and discrimination in ai: a cross-disciplinary perspective,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Bias and discrimination in ai: a cross-disciplinary perspective,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.849591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965dbf22-6d53-44ca-9b43-c586e24a3e92 · outbound

This paper cites Online manipulation: Hidden influences in a digital world,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Online manipulation: Hidden influences in a digital world,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.993883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f913b0cc-6b83-4396-ab76-ecdb735c7cd0 · outbound

This paper cites Privacy in human-ai romantic relationships: Concerns, boundaries, and agency,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Privacy in human-ai romantic relationships: Concerns, boundaries, and agency,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.474942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ab686e7-a23f-45e2-8386-36f53ab7b1bc · outbound

This paper cites Toward a field of intersectionality studies: Theory, applications, and praxis,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Toward a field of intersectionality studies: Theory, applications, and praxis,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:21.572173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b97a9dc-d73c-44ab-a6be-5fefc5fdcd05 · outbound

This paper cites an unresolved cited work.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Unresolved cited work

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:22.258850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06aaa01-fe52-42ee-9854-7435fd2363af · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents,.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Qwen3.5: Accelerating productivity with native multimodal agents,

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:22.375901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63a0ea68-d221-44e1-868d-f891db2e7bac · outbound

This paper cites Available: https://csrc.nist.gov/pubs/conference/ 1992/10/13/rolebased-access-controls/final.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Available: https://csrc.nist.gov/pubs/conference/ 1992/10/13/rolebased-access-controls/final

Reference 1992

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:16.955281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f479da6-3954-4e37-92eb-55b2c20d9856 · outbound

This paper cites Available: https://eur-lex.europa.eu/eli/reg/ 2017/745/oj.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Available: https://eur-lex.europa.eu/eli/reg/ 2017/745/oj

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:14.721646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5dcd6f-7b8d-47b0-b5e1-2a6881b584bd · outbound

This paper cites Available: https://georgetownlawtechreview.

Security and Privacy in Agentic AI: Grand Challenges and Future Directions Available: https://georgetownlawtechreview

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T08:24:22.088210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers