FedUP: Efficient pruning-based federated unlearning for model poisoning attacks

Federated Learning (FL) can be vulnerable to attacks such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clients is challenging because their collaboration in unlearning cannot be assumed. This work presents FedUP, a lightweight FU algorithm designed to efficiently mitigate malicious clients’ influence by pruning specific connections within the attacked model. FedUP achieves efficiency by relying only on clients’ weights from the last training round before unlearning to identify which connections to inhibit. Isolating malicious influence is non-trivial because benign and malicious updates may overlap. FedUP addresses this by selecting and zeroing the highest-magnitude weights that diverge most between the latest updates from benign and malicious clients while preserving benign information. We evaluate FedUP under a strong adversarial threat model, where up to 50 % − 1 of the clients may be malicious and have full knowledge of the aggregation process, including adaptive attackers aware of FedUP’s pruning strategy. The evaluation covers IID and Non-IID data, label-flipping and backdoor attacks, imperfect detection, and comparisons with state-of-the-art FU solutions. In our experiments, FedUP reduces malicious influence to levels comparable to retraining from scratch while preserving benign performance, achieving effective unlearning while consistently being faster and requiring less storage than the state of the art.

Authors

Institutions

Publication Details

Journal
Journal of Information Security and Applications
Published
2026-11-19
DOI
https://doi.org/10.1016/j.jisa.2026.104704
Citations
5
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
3.87
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

FedUP: Efficient pruning-based federated unlearning for model poisoning attacks

Rebecca Montanari, Nicolò Romandini, Luca Foschini, Cristian Borcea
5 citations
Journal of Information Security and Applications
Privacy-Preserving Technologies in Data
3.87
article

FedUP: Efficient pruning-based federated unlearning for model poisoning attacks

Rebecca Montanari, Nicolò Romandini, Luca Foschini, Cristian Borcea
article en
5 citations

Abstract

Federated Learning (FL) can be vulnerable to attacks such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clients is challenging because their collaboration in unlearning cannot be assumed. This work presents FedUP, a lightweight FU algorithm designed to efficiently mitigate malicious clients’ influence by pruning specific connections within the attacked model. FedUP achieves efficiency by relying only on clients’ weights from the last training round before unlearning to identify which connections to inhibit. Isolating malicious influence is non-trivial because benign and malicious updates may overlap. FedUP addresses this by selecting and zeroing the highest-magnitude weights that diverge most between the latest updates from benign and malicious clients while preserving benign information. We evaluate FedUP under a strong adversarial threat model, where up to 50 % − 1 of the clients may be malicious and have full knowledge of the aggregation process, including adaptive attackers aware of FedUP’s pruning strategy. The evaluation covers IID and Non-IID data, label-flipping and backdoor attacks, imperfect detection, and comparisons with state-of-the-art FU solutions. In our experiments, FedUP reduces malicious influence to levels comparable to retraining from scratch while preserving benign performance, achieving effective unlearning while consistently being faster and requiring less storage than the state of the art.

Journal of Information Security and ApplicationsVol. 104
New Jersey Institute of Technology (US), University of Bologna (IT)
Openalex Percentile: Top 6%
Privacy-Preserving Technologies in Data
3.87
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon