Data Leakage in Tabular Federated Learning. (arXiv:2210.01785v1 [cs.LG])

While federated learning (FL) promises to preserve privacy in distributed
training of deep learning models, recent work in the image and NLP domains
showed that training updates leak private data of participating clients. At the
same time, most high-stakes applications of FL (e.g., legal and financial) use
tabular data. Compared to the NLP and image domains, reconstruction of tabular
data poses several unique challenges: (i) categorical features introduce a
significantly more difficult mixed discrete-continuous optimization problem,
(ii) the mix of …

arxiv data data leakage federated learning tabular