.png){kind=icon}
.png){kind=icon}
Return
Model Hijacking Attack in Federated Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2026.3666296.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications. However, its remarkable success has been accompanied by various attacks. Recently, the model hijacking attack has shown that ML models can be hijacked to execute tasks different from their original tasks, which increases both accountability and parasitic computational risks. Nevertheless, thus far, this attack has only focused on centralized learning. In this work, we broaden the scope of this attack to the federated learning domain, where multiple clients collaboratively train a global model without sharing their data. Specifically, we present the first-of-its-kind hijacking attack against the global model in federated learning, namely HijackFL. The adversary aims to force the global model to perform a different task (called hijacking task) from its original task without the server or benign client noticing. To accomplish this, unlike existing methods that use data poisoning to modify the target model’s parameters, HijackFL searches for pixel-level perturbations based on their local model (without modifications) to align hijacking samples with the original ones in the feature space. When performing the hijacking task, the adversary applies these perturbations to the hijacking samples, compelling the global model to identify them as original ones and predict them accordingly. Extensive experiments demonstrate HijackFL significantly outperforms baselines, e.g., 92.75% vs. 10%. We further investigate the factors that affect its performance and discuss possible defenses to mitigate its impact. Code is available at https://github.com/zhenglisec/HijackFL
Keywords:
Machine learning
federated learning
security
model hijacking
dataset manipulation
Journal
IF:
8
Papers:
5.2K
Citations:
2.3W
Organization
View more organizations