New algorithm reconstructs PII from finetuned language models

By PulseAugur Editorial · [1 sources] · 2026-05-12 15:29

Researchers have developed a new decoding algorithm called COVA to reconstruct personally identifiable information (PII) from supervised finetuned language models. The study focused on sensitive domains like medical and legal settings, demonstrating that an adversary with even partial knowledge of the fine-tuning dataset can infer sensitive user data. The effectiveness of PII reconstruction varied by PII type, highlighting significant privacy risks associated with current fine-tuning practices. AI

IMPACT Reveals significant privacy risks in LLM fine-tuning, potentially impacting data handling and model deployment strategies.

RANK_REASON Academic paper detailing a new method for reconstructing PII from finetuned language models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

paper
safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

arXiv cs.CL TIER_1 English(EN) · Alina Oprea · 2026-05-12 15:29

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to domain-specific, instruction-following tasks. SFT datasets, composed of instruction-response pairs, often include user-provided info…

COVERAGE [1]

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

RELATED ENTITIES

RELATED TOPICS