Incorrect placement of Prevention & Mitigation step for LLM #10

[harissohail55]

For the LLM10: Model Theft section, the second entry for "Common Examples of Vulnerabilities", should be shifted down to the "Prevention and Mitigation strategies" section.

Here is the entry:
"Use a centralized ML Model Inventory or Registry for ML models used in production.
baving a centralized model registry prevents unauthorized access to ML Models via
access controls, authentication, and monitoring/logging capability which are good
foundations for governance. baving a centralized repository is also beneficial for
collecting data about algorithms used by the models for the purposes of compliance,
risk assessments, and risk mitigation"

[github-actions]

👋 Thanks for reporting! Please ensure labels are applied appropriately to the issue so that the workflow automation can triage this to the correct member of the core team

[github-actions]

👋 Thanks for reporting! Please ensure labels are applied appropriately to the issue so that the workflow automation can triage this to the correct member of the core team

[GangGreenTemperTatum]

Hi @harissohail55 , thanks for raising! I think you are looking at an old entry version perhaps
see updated version
https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/blob/main/2_0_vulns/LLM10_ModelTheft.md
and the website

[harissohail55]

Hey @GangGreenTemperTatum, thanks for the heads up. Yep, I was looking at version 1.1. Didn't see that 2.0 had been released. On the main OWASP website - https://owasp.org/www-project-top-10-for-large-language-model-applications/, it sill only shows Version 1.1.0 as the current version:

[GangGreenTemperTatum]

thanks, we havent yet announced an official v2 :)