AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Natural Identifiers for Privacy and Data Audits in Large Language Models

Lorenzo Rossi, Bartłomiej Marek, Franziska Boenisch, Adam Dziedzic

ICLR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase number of NIDs in the GSM8K suspect set from 50 to 100 (ablation)NID dataset inference · GSM8K task-specific NIDsp-value: 8.43\times10^{-4} -> 1.60\times10^{-6}Improved
increase number of NIDs in the suspect set (ablation)NID dataset inference · Pile and Dolma subsetsp-valueImproved
add stronger MIAs (CAMIA, SURP) to the DI features (ablation)NID dataset inference · Pile DIp-valueImproved
generate GIDs from a distribution mismatching the NIDs (e.g. changed casing) (ablation)NID dataset inference · Pile DIfalse positive rateHurt
use natural NIDs instead of injected canaries (ablation)NID dataset inference · Pile DIp-valueNo clear effect
use longer or more structured NID formats (SHA-512, Java serialization) rather than MD5 (ablation)NID dataset inference · DI by identifier typep-valueImproved
increase candidate set cardinality c from 2 to 8 or 32 (ablation)post-hoc DP auditing · Pythia DP-SGD finetuning, large epsilonepsilon lower boundImproved
increase candidate set cardinality c (ablation)post-hoc DP auditing · Pythia DP-SGD finetuning, small epsilonepsilon lower boundHurt
use Hinge instead of Loss as MIA (ablation)NID vs GID MIA · Pile GitHub trainAUC: 71.8 -> 71.8No clear effect
use ReCALL instead of Loss as MIA (ablation)NID vs GID MIA · Pile GitHub trainAUC: 71.8 -> 50.6Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy