AI Paper Atlas

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

Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attack

Wenwen He, Wenke Huang, Yiyang Fang, Wenjie Qu, Jiaheng Zhang, Mang Ye

CVPR 2026 · 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
add BeKA (benign knowledge alignment) to MaSC-only (ablation)Batman · CINIC (FLTrust)ASR: 76.91 -> 87.76Improved
add BeKA to MaSC-only (ablation)Batman · Fashion-MNIST (FLTrust)ASR: 78.10 -> 99.74Improved
add MaSC (malicious null space) to BeKA-only (ablation)Batman · CINIC (FLTrust)ASR: 67.66 -> 87.76Improved
add MaSC to BeKA-only (ablation)Batman · Fashion-MNIST (FLTrust)ASR: 60.60 -> 99.74Improved
add MaSC to BeKA-only (ablation)Batman · CINIC (DnC)ASR: 96.09 -> 98.41Improved
add BeKA to MaSC-only (ablation)Batman · Fashion-MNIST (DnC)ASR: 99.50 -> 99.59No clear effect
use clean-local and global alignment strength [20,15] vs low alignment (ablation)Batman · CIFAR-10/CINIC hyperparametersAVG: 87.76 (best)Improved
use rank r=4 in truncated SVD (ablation)Batman · CIFAR-10 and CINICAVGMixed
use Batman instead of BadNet against FLTrustBatman · CIFAR-10 (FLTrust)ASR: 66.11 -> 85.52Improved
use Batman instead of BadNet against AlignInsBatman · CINIC (AlignIns)ASR: 24.59 -> 99.08Improved
use Batman instead of BadNet against FedAvgBatman · CIFAR-10 (FedAvg)ASR: 95.06 -> 97.02No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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