4 papers
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
Na Li, Boyu Kuang, Hongsheng Hu +4
To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image…
From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
Qirui Huang, Na Li, Hongsheng Hu +3
To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age es…
CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
Na Li, Yansong Gao, Hongsheng Hu +2
Model compression is crucial for minimizing memory storage and accelerating inference in deep learning (DL) models, including recent foundation models like large language models (L…
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Na Li, Chunyi Zhou, Yansong Gao +4
Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the right to be f…