AI Paper Atlas

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

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

Tiansheng Huang, Sihao Hu, Ka-Ho Chow, Fatih Ilhan, Selim Furkan Tekin, Ling Liu

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 8 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 gradient-based recovery instead of random recovery (ablation)Lockdown · CIFAR10 IIDASR (%): 13.0 -> 1.4Improved
use gradient-based recovery instead of random recovery (ablation)Lockdown · CIFAR10 IIDBenign Acc (%): 91.1 -> 90.7Hurt
use gradient-based recovery instead of random recovery (ablation)Lockdown · CIFAR10 Non-IIDASR (%): 17.2 -> 2.2Improved
use ERK initialization instead of uniform (ablation)Lockdown · CIFAR10 IIDBenign Acc (%): 81.7 -> 90.1Improved
use ERK initialization instead of uniform (ablation)Lockdown · CIFAR10 Non-IIDBenign Acc (%): 75.5 -> 86.1Improved
use ERK initialization instead of uniform (ablation)Lockdown · CIFAR10 IIDASR (%): 5.7 -> 7.1No clear effect
increase sparsity s from 0 to 0.75 (ablation)Lockdown · CIFAR10 IIDASR (%): 68.4 -> 7.1Improved
increase sparsity s from 0.75 to 0.9 (ablation)Lockdown · CIFAR10 IIDBenign Acc (%): 90.1 -> 88.3Hurt
set initial pruning rate alpha0 from 0 to 1e-4 (ablation)Lockdown · CIFAR10 IIDASR (%): 49.4 -> 7.1Improved
raise alpha0 from 1e-4 to 1e-1 (ablation)Lockdown · CIFAR10 IIDBenign Acc (%): 90.1 -> 87.0Hurt
enlarge alpha0 to 0.1 against FixMask attack (ablation)Lockdown · CIFAR10 IID FixMaskASR (%): 63.5 -> 3.5Improved
add heterogeneous mask initialization with alpha0=0.1 against FixMask (ablation)Lockdown · CIFAR10 Non-IID FixMaskASR (%): 4.6 -> 3.7No clear effect

Later papers that compared with this method

2 later accepted papers report LockDown as a baseline in their results tables; 2 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