AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences

Richardeau Gurvan, Gohar Dashyan, Erwan Le Merrer, Gilles Tredan

ICML 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs · 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
use instance-level fingerprinting (FLIPS) instead of adapted LLMmapinstance identification · 237 instances, closed-setaccuracy: 35% -> 96%Improved
replace XGBoost classifier with other classifiers (ablation)FLIPS · closed-set, Nt=8accuracy: 96.8% -> 68.1% (Gradient Boosting)Hurt
increase verification queries Nt from 1 to 8 (ablation)FLIPS · open-setaccuracy: 64% -> 90%Improved
increase verification queries for LLMmap from 4 to 8 (ablation)LLMmap-IF · closed-setaccuracyNo clear effect
use different token pairs across queries rather than the same pair repeatedly (ablation)FLIPS · closed-setaccuracyImproved
raise sampling temperature from 0.4 to 1.0 (ablation)target instances · open-set, Nt=8recall: 99% -> 87%Hurt
abliterated variant of a model (ablation)FLIPS · open-set, Nt=8recall: 77% average vs 87%-99% for other variationsHurt
truncate all bit sequences to fixed 100 bits (ablation)FLIPS · closed-set and open-setaccuracyNo clear effect
use the 0-1 token pair instead of arbitrary token pairs (ablation)FLIPS · closed-set, Nt=1fingerprinting accuracyHurt
use alpha-quantile threshold from training data instead of oracle test threshold (ablation)FLIPS open-set · open-set, Nt=8AUROC: 0.947 -> 0.938No clear effect
better randomness of generated sequences (higher NIST score)instances · closed-set, Nt=1fingerprinting accuracyHurt

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