AI Paper Atlas

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

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

Haonan Yan, Wenjing Zhang, Qian Chen, Xiaoguang Li, Wenhai Sun, HUI LI, Xiaodong Lin

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning · 7 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 proactive client testing and multi-round trust scoring instead of passive defensesFederated learning · MNIST, CIFAR-10, Purchase, and FEMNIST under model-poisoning attacksaccuracyMixed
Use RECESS rather than FLDetectorCIFAR-10 IID · AGR-agnostic Min-Max attackaccuracy: 0.5178 -> 0.6286Improved
Use RECESS rather than FLDetectorCIFAR-10 Non-IID 0.8 · Optimization attackaccuracy: 0.3544 -> 0.6018Improved
Use RECESS rather than FLDetectorFEMNIST · AGR-agnostic Min-Max attackaccuracy: 0.5616 -> 0.7850Improved
Use RECESS rather than FedAvgCIFAR-10, ResNet20 · Optimization attackaccuracy: 0.1718 -> 0.8173Improved
Use RECESS with Median aggregation instead of weighted averagingRECESS · CIFAR-10 label-flipping attackModel Accuracy: 0.4415 -> 0.6148Improved
Use RECESS with Median aggregation instead of weighted averagingRECESS · CIFAR-10 scaling attackAttack Success Rate: 1.0 -> 0.0Improved
Increase detection frequency from 0 to 10 (ablation)RECESS · FEMNIST adaptive optimization attack, white-boxaccuracy: 0.2482 -> 0.3456Improved
Increase detection frequency from 10 to 50 (ablation)RECESS · FEMNIST adaptive optimization attack, white-boxaccuracy: 0.3456 -> 0.6847Improved
Increase detection frequency from 50 to 100 (ablation)RECESS · FEMNIST adaptive optimization attack, white-boxaccuracy: 0.6847 -> 0.7815Improved
Increase detection frequency from 100 to 200 (ablation)RECESS · FEMNIST adaptive optimization attack, white-boxaccuracy: 0.7815 -> 0.8011Improved
Increase the trust-score deduction baseline (ablation)RECESS · Model-poisoning detectiondetection speedMixed

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