Model techniques map
Techniquesevaluationhuman & real-world evaluation

specific method · filed under evaluation

Automated red-teaming loop

Uses an attacker model to iteratively rewrite injected instructions against a defender model.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we use an automated red-teaming loop in which an attacker model iteratively rewrites the injected instruction against a defender model

usedunclearin Agentic safety teacher for Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under evaluation :: human & real-world evaluation.