AI Paper Atlas

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

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

Hangfan Zhang, Jinyuan Jia, Jinghui Chen, Lu Lin, Dinghao Wu

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 31 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 adversarial adaptation loss (ablation)A3FL · CIFAR-10 FedAvg P=20, 1000 rounds after attackASR (%): 69.01 -> 84.65Improved
add adversarial adaptation loss (ablation)A3FL · CIFAR-10 FedAvg P=20, 500 rounds after attackASR (%): 93.35 -> 97.66Improved
add adversarial adaptation loss (ablation)A3FL · CIFAR-10 FedAvg P=20, at attack endASR (%): 100.0 -> 100.0No clear effect
vary trigger size from 3x3 to 10x10 (ablation)A3FL · CIFAR-10 Norm ClippingASR (%): best-worst gap 1.75%No clear effect
vary lambda0 over 0 to 1 (ablation)A3FL · CIFAR-10 Norm ClippingASR (%): gap 0.5%No clear effect
use A3FL instead of baseline attacksbackdoor attack on FL · CIFAR-10 Norm Clipping, 1 compromised clientASR (%): 13.9 -> 99.75Improved
attack with A3FL vs no attackglobal model utility · CIFAR-10 across defensesclean accuracy (%): max drop 0.28%No clear effect

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