technique

Shuffle Model

techniqueactiveprovisionalshuffle-model-c828ea14·1 events·first seen 15d ago

Aliases: Shuffle Model

Co-occurring entities

Differential Privacy Privacy Inference Attack IntraShuffler Heterogeneous Differential Privacy Federated Learning

More like this (12)

IntraShuffler Language Models are Few-Shot Learners Neural Surrogate Models Masked Diffusion Models discrete diffusion models Superposition Model (neural networks)Representation-Conditioned Diffusion Models dynamics randomization randomized collage Monte Carlo Dropout masked-token modeling open-checkpoint models

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