FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abacha, Fatima Z., Teo, Sin G., Wu, Yuanxiang, Cordeiro, Lucas C., Mustafa, Mustafa A.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916001759625216
author Abacha, Fatima Z.
Teo, Sin G.
Wu, Yuanxiang
Cordeiro, Lucas C.
Mustafa, Mustafa A.
author_facet Abacha, Fatima Z.
Teo, Sin G.
Wu, Yuanxiang
Cordeiro, Lucas C.
Mustafa, Mustafa A.
contents Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial false-positive rates under realistic non-independent and identically distributed (non-IID) data, incorrectly flagging benign clients and degrading model accuracy even when adversaries are correctly identified. We present FedSurrogate, a novel backdoor defense that addresses this limitation by combining bidirectional gradient alignment filtering with layer-adaptive anomaly detection. FedSurrogate performs selective clustering on security-critical layers identified via directional divergence analysis, concentrating the detection signal on a low-dimensional subspace. A bidirectional soft-filtering stage screens trusted clients for residual contamination while rescuing false positives from suspects, substantially reducing misclassifications under heterogeneous conditions. Rather than removing confirmed malicious updates, FedSurrogate replaces them with downscaled surrogate updates from structurally similar benign clients, preserving gradient diversity while neutralising adversarial influence. Extensive evaluations demonstrate that FedSurrogate maintains false-positive rates below 10% across all datasets and attack types, compared to 31-32% for the nearest comparably effective baseline, while achieving superior main-task accuracy and maintaining attack success rates below 2.1% across all tested datasets and attack types under challenging non-IID settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11122
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
Abacha, Fatima Z.
Teo, Sin G.
Wu, Yuanxiang
Cordeiro, Lucas C.
Mustafa, Mustafa A.
Cryptography and Security
Machine Learning
Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial false-positive rates under realistic non-independent and identically distributed (non-IID) data, incorrectly flagging benign clients and degrading model accuracy even when adversaries are correctly identified. We present FedSurrogate, a novel backdoor defense that addresses this limitation by combining bidirectional gradient alignment filtering with layer-adaptive anomaly detection. FedSurrogate performs selective clustering on security-critical layers identified via directional divergence analysis, concentrating the detection signal on a low-dimensional subspace. A bidirectional soft-filtering stage screens trusted clients for residual contamination while rescuing false positives from suspects, substantially reducing misclassifications under heterogeneous conditions. Rather than removing confirmed malicious updates, FedSurrogate replaces them with downscaled surrogate updates from structurally similar benign clients, preserving gradient diversity while neutralising adversarial influence. Extensive evaluations demonstrate that FedSurrogate maintains false-positive rates below 10% across all datasets and attack types, compared to 31-32% for the nearest comparably effective baseline, while achieving superior main-task accuracy and maintaining attack success rates below 2.1% across all tested datasets and attack types under challenging non-IID settings.
title FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2605.11122