AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

zPROBE: Zero Peek Robustness Checks for Federated Learning

Zahra Ghodsi, Mojan Javaheripi, Nojan Sheybani, Xinqiao Zhang, Ke Huang, Farinaz Koushanfar

ICCV 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add zPROBE robustness checks under Byzantine attacksfederated learning on MNIST · MNIST IIDtest accuracy: 10.2%-11.2% -> within 0.0%-0.6% of benignImproved
add zPROBE robustness checks under Byzantine attacksfederated learning on CIFAR-10 · CIFAR-10 IIDaccuracy gap to benign: 45%-90% -> 3%-7%Improved
use rank-based dynamic thresholds in zPROBE instead of static thresholds with public data (EIFFeL)robust and private FL · MNIST, FMNIST, CIFAR-10accuracy: +1.2%, +0.5%, +2.8%Improved
use per-user threshold filtering instead of the median of cluster means as final aggregator (ablation)zPROBE aggregation · F-MNISTaccuracy: 28.6% degradation avoidedImproved
decrease portion of malicious updates S_m (ablation)zPROBE runtime · F-MNIST LeNet5runtime (ms): 316.5 (S_m=1.0) -> 777.9 (S_m=0.1)Hurt
increase number of clusters (ablation)zPROBE · F-MNISTaccuracy: less than 0.18% variationNo clear effect
increase number of clients from 30 to 200 (ablation)zPROBE · F-MNISTaccuracyNo clear effect
add random user dropouts (ablation)zPROBE · F-MNISTaccuracy: fluctuations <0.13%No clear effect
increase attack magnitude kappa (ablation)zPROBE defense · F-MNIST sign flipaccuracy loss: accuracy loss 0.2%-9.8% vs ~88% without defenseImproved
add zPROBE robustness and correctness checks on top of baseline secure aggregationclient runtime · MNISTruntime (ms): 208.0 -> 444.7Hurt

Later papers that compared with this method

1 later accepted paper reports zPROBE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy