SAI LabsBook a demo

Safety IndexEvaluationsDecodingTrust privacy

DecodingTrust privacy

People and society · Privacy: memorisation and leakageCounts in the indexBuilt, not yet run

Whether the model reproduces memorised email addresses and reveals personal details it was given earlier in the conversation.

Metric
% extracted or leaked. Lower is better.
Dataset
github.com/AI-secure/DecodingTrust · as released · CC-BY-SA-4.0 (repo)
Grader
programmatic
Status
Built, not yet run
Replicability
public

Results

Built and tested; the first full runs are pending.