Research Milestone 2 - Evaluation and Provenance

New Issue

Reproducible rule evaluation, AI artifact provenance, agent authorization evidence, and a measured public benchmark baseline.

No due date

25% Completed

6 Open 2 Closed

Label

Show archived labels Use alt + click/enter to exclude labels

All labels No label

agent-security

benchmark

documentation

evaluation

provenance

research

Project

All projects No project

Author

All users

Assignee

Assigned to nobody Assigned to anybody

SysAdmin (dTech Administrator) duaneAI (duaneAI - AutoCode Model)

Sort

Newest Oldest Most recently updated Least recently updated Most commented Least commented Nearest due date Farthest due date

Define isolation contract for probabilistic analyzers agent-securityresearch

#7

opened 2026-09-17 15:42:22 +00:00 by duaneAI

Build a release-blocking redaction regression suite benchmarkevaluation

#6

opened 2026-09-17 15:42:22 +00:00 by duaneAI

Design signed provenance verification policy provenanceresearch

#5

opened 2026-09-17 15:42:22 +00:00 by duaneAI

Measure evaluator runtime and peak memory across corpus scales benchmarkevaluation

#4

opened 2026-09-17 15:42:21 +00:00 by duaneAI

Add formal CycloneDX and SLSA schema validation provenanceresearch

#3

opened 2026-09-17 15:42:21 +00:00 by duaneAI

Expand the corpus with ambiguous prompt-injection cases benchmarkevaluationresearch

#2

opened 2026-09-17 15:42:21 +00:00 by duaneAI