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
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
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]