Skip to content

Add Security and Privacy Terms for WG review #56

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kdruckman wants to merge 1 commit into
base: main
Choose a base branch
from
+54 −0
Open

Add Security and Privacy Terms for WG review #56

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 54 additions & 0 deletions taxonomy/taxonomy-data.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -252,5 +252,59 @@ window.AAIF_TAXONOMY = [
relatedTerms: [],
contrastsWith: [],
workgroups: ['Governance, Risk & Regulatory Alignment', 'Workflows & Process Integration']
},

// ---------------------------------------------------------------------
// Security & Privacy
// ---------------------------------------------------------------------
{
term: 'Agent derailment',
category: '',
aliases: [],
broaderTerm: null,
definition: 'An unintended deviation in an AI agent\'s behavior that causes it to pursue goals or take actions outside its intended scope, without malicious external cause.',
relatedTerms: [],
contrastsWith: [],
workgroups: ['Security & Privacy']
},
{
term: 'Agent sabotage',
category: '',
aliases: [],
broaderTerm: null,
definition: 'Deliberate manipulation of an AI agent\'s behavior by an external party, causing it to act against its intended purpose, to an elevated degree with severe or criminal consequences.',
relatedTerms: [],
contrastsWith: [],
workgroups: ['Security & Privacy']
},
{
term: 'Agent mishandling/misuse',
category: '',
aliases: [],
broaderTerm: null,
definition: 'Deliberate manipulation of an AI agent\'s behavior by an external party, causing it to act against its intended purpose.',
relatedTerms: [],
contrastsWith: [],
workgroups: ['Security & Privacy']
},
{
term: 'Rogue agent',
category: '',
aliases: [],
broaderTerm: null,
definition: 'An AI agent that operates outside its authorized boundaries, whether due to compromise, misconfiguration, or emergent behavior.',

@awfrazer awfrazer Sep 1, 2026 •
edited
Loading

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does intention factor in here? Thinking out loud, it could be operating outside of authorized or intended boundaries.

relatedTerms: [],
contrastsWith: [],
workgroups: ['Security & Privacy']
},
{
term: 'Privacy-preserving execution',
category: '',
aliases: [],
broaderTerm: null,
definition: 'Patterns in which an AI agent can operate on encrypted or protected data without exposing the underlying content, using techniques such as zero-knowledge proofs or trusted execution environments.',
relatedTerms: [],
contrastsWith: [],
workgroups: ['Security & Privacy']
}
];