Sparsity in neural networks can improve their privacy
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Can sparsity improve the privacy of neural networks?
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
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 LearningCutClean: Neural Network Pruning for Privacy-Preserving Inference
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 PruningDefending Membership Inference Attacks via Privacy-aware Sparsity Tuning
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
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