Sae Furukawa
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
This paper investigates the privacy risk of reconstructing Personally Identifiable Information (PII) from Large Language Models (LLMs) that have undergone Supervised Finetuning (SFT), proposing a novel decoding algorithm (COVA) for defense evaluation.
Highlighted terms show continued research focus across papers