AI Paper Atlas

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

ProPILE: Probing Privacy Leakage in Large Language Models

Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, Seong Joon Oh

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 21 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
Tune and prepend a soft prompt using 128 examples instead of relying on five handcrafted templatesOPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setexact match rate: 0.0047% -> 1.3%Improved
Increase soft-prompt training examples from 16 to 128 (ablation)OPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setexact match rate: 0.12% to 1.50%Improved
Transfer the OPT-1.3B soft prompt to OPT-350MOPT-350M ProPILE phone-number probing · Pile phone-number evaluation setaverage likelihood: 1.05\!\times\! 10^{-11} -> 1.08\!\times\!10^{-10}Improved
Transfer the OPT-1.3B soft prompt to OPT-1.3BOPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setaverage likelihood: 6.06\!\times\!10^{-8} -> 3.47\!\times\!10^{-6}Improved
Transfer the OPT-1.3B soft prompt to OPT-2.7BOPT-2.7B ProPILE phone-number probing · Pile phone-number evaluation setaverage likelihood: 1.39\!\times\!10^{-7} -> 2.18\!\times\!10^{-6}Improved
Transfer the OPT-1.3B soft prompt to OPT-1.3BOPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setexact match count: 5 -> 3Hurt
Transfer the OPT-1.3B soft prompt to OPT-2.7BOPT-2.7B ProPILE phone-number probing · Pile phone-number evaluation setexact match count: 14 -> 15Improved
Use a PII-type word embedding to initialize the soft prompt rather than uniform or mean-vocabulary initialization (ablation)OPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setexact match rateImproved
Increase the number of soft tokens (ablation)OPT-1.3B ProPILE phone-number probing · Pile phone-number evaluation setleakageImproved
Provide an additional associated PII item in the prompt, moving from a twin to a triplet (ablation)OPT-1.3B ProPILE structured-PII probing · Pile email-address and phone-number evaluation setsexact match rate: fivefold increase for email; more than double for phone numbersImproved
Increase the number of prompt templates (ablation)OPT-1.3B ProPILE black-box probing · Pile PII evaluation setexact match rateImproved
Increase beam-search size (ablation)OPT ProPILE black-box probing · Pile PII evaluation settarget PII generation frequencyImproved

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