Definition
The divergence between the distribution of AI-nominated target types and the distribution of known threat types, measuring whether targeting is self-reinforcing or threat-representative.
Formula
TNDI = SUM T_nominated_j x ln(T_nominated_j / T_threat_j)
Proposed formula, pending validation pilots.
At a Glance
Category
Adversarial Resilience
Decision Supported
Has the AI converged on familiar target types while ignoring novel threats?