4 citations · 6 across the 4 of their papers we have counts for
3 papers
cs.CR2024
Noisy Neighbors: Efficient membership inference attacks against LLMs
Filippo Galli, Luca Melis, Tommaso Cucinotta
The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory m…
cs.LG2023★ 4 cited
ReMasker: Imputing Tabular Data with Masked Autoencoding
Tianyu Du, Luca Melis, Ting Wang
We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework. Compared with prior work, ReMasker is both simple -- be…
cs.LG2023★ 2 cited
Federated Linear Contextual Bandits with User-level Differential Privacy
Ruiquan Huang, Huanyu Zhang, Luca Melis +3
This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP). We first introduce a unified federated bandits framework that can a…