paper-with-me

홈 › Papers

Sparsity in neural networks can improve their privacy

2023-04-20 · Antoine Gonon, Léon Zheng, Clément Lalanne, Quoc-Tung Le, Guillaume Lauga, Can Pouliquen

This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the task at hand. This empirical study completes and extends existing literature.

📄 PDF Abstract BibTeX arXiv:2304.10553

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Can sparsity improve the privacy of neural networks?

2023-04-11 · Antoine Gonon, Léon Zheng, Clément Lalanne, Quoc-Tung Le 외

Sparse neural networks are mainly motivated by ressource efficiency since they use fewer parameters than their dense counterparts but still reach comparable accuracies. This article empirically investigates whether spars…

Multi-View Graph Feature Propagation for Privacy Preservation and Feature Sparsity

2025-10-13 · Etzion Harari, Moshe Unger arxiv

Graph Neural Networks (GNNs) have demonstrated remarkable success in node classification tasks over relational data, yet their effectiveness often depends on the availability of complete node features. In many real-world…

Node ClassificationGraph Learning

CutClean: Neural Network Pruning for Privacy-Preserving Inference

2026-08-13 · Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise, Enzo Tartaglione arxiv

Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to tradi…

Network Pruning

Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning

2024-10-09 · Qiang Hu, Hengxiang Zhang, Hongxin Wei

Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model. Previous Weight regularizations (e.g., L1…

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

2023-08-17 · Phillip Rust, Anders Søgaard

Language models such as mBERT, XLM-R, and BLOOM aim to achieve multilingual generalization or compression to facilitate transfer to a large number of (potentially unseen) languages. However, these models should ideally a…

FairnessXLM-R