technique

Heterogeneous Differential Privacy Federated Learning

techniqueactiveprovisionalheterogeneous-differential-privacy-federated-learning-271372a1·1 events·first seen 15d ago

Aliases: Heterogeneous Differential Privacy Federated Learning

Co-occurring entities

Differential Privacy Privacy Inference Attack IntraShuffler Shuffle Model

More like this (12)

Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning Federated Learning Differential Privacy Range Penalization: Theoretical Insights with Applications in Federated Learning FlashbackCL: Mitigating Temporal Forgetting in Federated Learning Supervised Semantic Differential Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning Disentangled Representation Learning Knowledge Editing in Masked Diffusion Language Models Fully Homomorphic Encryption The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models Differential Attention

Recent events (1)

5arXiv · cs.LG·15d ago·source ↗

IntraShuffler: Privacy-Preserving Framework for Heterogeneous DP Federated Learning

This paper identifies a novel Privacy Inference Attack against heterogeneous differential privacy federated learning (HDP-FL) systems, where an honest-but-curious server exploits epsilon-aware aggregation and gradient denoising to infer client data distributions and link updates across rounds. To counter this, the authors propose IntraShuffler, a middleware framework that groups clients into privacy-compatible buckets and performs parameter-level shuffling within buckets, preserving epsilon-aware aggregation while disrupting persistent gradient structure. Experiments on four datasets show IntraShuffler reduces gradient recoverability by over 60% and drops surrogate inference accuracy from 0.78 to 0.33 with minimal utility loss.

AI Safety Research Enterprise Deployment Patterns Differential Privacy Privacy Inference Attack IntraShuffler +2 more