Draft:PLOT4AI
 | Review waiting, please be patient.
This may take 5 weeks or more, since drafts are reviewed in no specific order. There are 2,037 pending submissions waiting for review.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
Reviewer tools
|
| Submission declined on 26 January 2026 by Commandant Quacks-a-lot (talk). This submission is not adequately supported by reliable sources. Reliable sources are required so that information can be verified. If you need help with referencing, please see Referencing for beginners and Citing sources.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
This draft has been resubmitted and is currently awaiting re-review. |  |
Comment: Several sections and sentences are entirely unsourced. Make sure every fact has a source hooked to it. Best of luck! Commandant Quacks-a-lot (talk) 21:45, 26 January 2026 (UTC)
PLOT4AI (Practical Library Of Threats for Artificial Intelligence) is an open-source threat modeling methodology and threat library for identifying and discussing risks in artificial intelligence (AI) systems across the AI lifecycle. PLOT4AI is listed in the OECD AI Tools Catalogue[1] and has been referenced in academic literature and public-sector guidance on AI risks and privacy threat modeling.
Overview
[edit]PLOT4ai is a comprehensive threat modeling methodology designed for developers and deployers of AI systems to support the identification and mitigation of AI risks. It was inspired by collaborative threat modeling approaches such as LINDDUN GO and adapted for risks that are specific to AI/ML[2], inluding issues related to data governance, bias and discrimination, transparency, accountability, and security. The project is published under a 'Creative Commons Attribution-ShareAlike 4.0 International' license and contributions are welcomed by the author[3].
Threat library
[edit]The PLOT4AI library consists of more than 130 documented threats, grouped into eight categories[4]:
- Data and Data Governance
- Privacy and Data Protection
- Bias, Fairness and Discrimination
- Safety and Environmental Impact
- Cybersecurity
- Ethics and Fundamental Rights
- Transparency and Accessibility
- Accountability and Oversight
The threats are introduced in the form of elicitation questions and contains extensive documentation to help understand the risk. This supports a structured discussion and risk identification during the design, development, deployment, and monitoring of AI systems.
Card deck
[edit]PLOT4AI has been designed as a card game to support structured discussion during threat modeling sessions, including sessions involving participants with different backgrounds. The project provides an online digital version of the card deck.[5] Besides the possiblility to do it collaboratively remotely, it can also generate a report based on identified threats. A physical printed deck is also available through third-party retailers[6] and can be used during in-person sessions.
Availability
[edit]PLOT4ai is maintained in a public github repository and distributed with a Creative Commons license that permits commercial use, reuse and adaptation.
Use in research and guidance
[edit]PLOT4AI has been referenced in academic research on privacy threat modeling as well as AI risk analysis as an example of a threat library specific for AI that extends beyond traditional models which tend to be more security focused. Literature about privacy and security risks in machine learning systems references PLOT4AI as an approache for identifying AI-related threats.[7][8]
Public-sector guidance on AI privacy risks has also referenced PLOT4AI as a tool for identifying risks in AI systems, including large language models.[9]
Integration with OWASP Threat Dragon
[edit]PLOT4AI is a supported methodology in OWASP Threat Dragon, an open-source threat modeling tool maintained by the OWASP.[10] PLOT4AI is available alongside other threat modeling frameworks such as STRIDE and LINDDUN and can be selected as a methodology to perform the threat modeling.
See also
[edit]References
[edit]- ^ "PLOT4AI". OECD AI Tools Catalogue. Organisation for Economic Co-operation and Development.
- ^ "About". PLOT4ai.
- ^ "How to contriubte". PLOT4ai.
- ^ "Library". PLOT4ai.
- ^ "PLOT4AI assessment". PLOT4AI.
- ^ "PLOT4AI – A threat modeling library to build responsible AI". CyberSec Games.
- ^ Wuyts, Kim (2024). "Unraveling Privacy Threat Modeling Complexity". arXiv:2408.03578 [cs.CR].
- ^ Gallagher, Jonathan; Esfandiari, Yasaman; MacPhee, Callen; Warren, Michael (2025). "Provably effective detection of effective data poisoning attacks". arXiv:2501.11795 [cs.CR].
- ^ European Data Protection Board (2025). AI Privacy Risks and Mitigations in Large Language Models (LLMs) (PDF) (Report). European Data Protection Board. Retrieved 11 January 2026.
- ^ "OWASP Threat Dragon". OWASP. Open Web Application Security Project.