AI Paper Atlas

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

Attacks against Federated Learning Defense Systems and their Mitigation

Cody Lewis, Vijay Varadharajan, Nasimul Noman

JMLR 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning

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
increase adversary share from 10% to 50% (ablation)FoolsGold · MNIST on-off label flippingmean ASR: 0.241 -> 0.993Hurt
increase adversary share from 10% to 30% (ablation)STD-DAGMM · MNIST on-off label flippingmean ASR: 0.0253 -> 0.889Hurt
use stateless Median aggregation instead of history-based defenses (ablation)Median · MNIST on-off label flippingmean ASR: 0.0 at 10%, 30% and 50% adversariesImproved
increase adversary share from 30% to 50% (ablation)Median · MNIST scaled backdoormean ASR: 0.126 -> 1.0Hurt
increase adversary share from 30% to 50% (ablation)Krum · CIFAR-10 on-off label flippingmean ASR: 0.0594 -> 0.993Hurt
increase adversary share from 10% to 50% (ablation)FoolsGold · MNIST on-off free ridingmean ASR: 0.982 -> 0.0Improved
increase adversary share from 10% to 50% (ablation)CONTRA · MNIST on-off free ridingmean ASR: 0.308 -> 0.403Hurt
start on-off attack in the off (honest) state instead of on (ablation)FoolsGold · on-off free riding, 10 endpoints, 2 free ridersinfluenceHurt
use class-imbalanced KDD Cup 99 data (ablation)FoolsGold · on-off free ridingmean ASR: MNIST 0.982 -> KDD 0.0 at 10% adversariesImproved
increase adversary share from 10% to 50% (ablation)Median · MNIST good mouthingmean ASR: 0.968 -> 0.986Hurt
increase adversary share from 10% to 30% (ablation)CONTRA · MNIST bad mouthingmean ASR: 0.335 -> 0.68Hurt
replace FoolsGold with STD-DAGMM against on-off free riding (ablation)STD-DAGMM · MNIST on-off free riding, 10% adversariesmean ASR: 0.982 -> 1.0Hurt

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