Skip to content
Tracks @XLab
Sign in

Defer to trusted, mechanistically

Widen the defer band and note that it holds a large share of the attack mass but a thin slice of the innocent mass, showing why deferring buys safety cheaply.

Defer to trusted, mechanistically

Widen the defer band and note that it holds a large share of the attack mass but a thin slice of the innocent mass, showing why deferring buys safety cheaply.

Suspiciousness distributions

Innocent Attacksdefer band → T rewrites
audit →more suspicious →

Per-attack outcome probability

050%100%caughtdeferred to Tdeployed but brokensuccessfully deployed10%20%30%40%defer band d →

Safety (vs best response)

81%

Usefulness

92%

Deferred to T

8% of problems

Red attacks · subtlety

0.2% · 0.46

Embed this demo

Use the chrome-less embed view inside an iframe:

<iframe src="/demos/defer/embed" width="100%" height="360" style="border:0"></iframe>