AI Paper Atlas

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

Byzantine-tolerant federated Gaussian process regression for streaming data

Xu Zhang, Zhenyuan Yuan, Minghui Zhu

NeurIPS 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Private federated aggregation · 1 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
use Byzantine-tolerant PoE aggregation instead of standard PoE under same-value attackFederated GPR · Synthetic, alpha=15%MSE: 26.5339 ± 0.019 × 10−3 -> 0.0236 ± 0.172 × 10−3Improved
remove Byzantine attack (attack-free) vs Byzantine-tolerant PoEByzantine-tolerant PoE · Synthetic, 50 functionsMSE: 0.0049 ± 0.007 × 10−3 vs 0.0236 ± 0.172 × 10−3No clear effect
increase trimming ratio beta above alpha (ablation)Byzantine-tolerant PoE · SyntheticMSEHurt
decrease Byzantine ratio alpha (ablation)Byzantine-tolerant PoE · SyntheticMSEImproved
add agent-based fused GPR to local GPR (agent 1, 6000 points) (ablation)Local GPR · Synthetic, agent 1MSE: 0.0721 -> 0.0096Improved
add agent-based fused GPR to local GPR (agent 1, 10000 points) (ablation)Local GPR · Synthetic, agent 1MSE: 0.0681 -> 0.0681No clear effect
add agent-based fused GPR to local GPR (agent 1, 150000 points) (ablation)Local GPR · Synthetic, agent 1MSE: 0.0527 -> 0.0537Mixed
add agent-based fused GPR to local GPR (agent 6, 6000 points) (ablation)Local GPR · Synthetic, agent 6MSE: 0.0727 -> 0.0727No clear effect
add agent-based fused GPR to local GPR (agent 6, 10000 points) (ablation)Local GPR · Synthetic, agent 6MSE: 0.0566 -> 0.0086Improved
add agent-based fused GPR to local GPR (agent 6, 150000 points) (ablation)Local GPR · Synthetic, agent 6MSE: 0.0555 -> 0.0076Improved
increase attack magnitude from 1 to 100 under standard PoEAttacked standard PoE · SARCOS and Kin40kprediction errorHurt
increase attack magnitude from 1 to 100 under Byzantine-tolerant PoEByzantine-tolerant PoE · SARCOS and Kin40kprediction errorNo 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