@Article{cmes.2025.071190,
AUTHOR = {Seunghan Kim, Changhoon Lim, Gwonsang Ryu, Hyunil Kim},
TITLE = {How Robust Are Language Models against Backdoors in Federated Learning?},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {145},
YEAR = {2025},
NUMBER = {2},
PAGES = {2617--2630},
URL = {http://www.techscience.com/CMES/v145n2/64565},
ISSN = {1526-1506},
ABSTRACT = {Federated Learning enables privacy-preserving training of Transformer-based language models, but remains vulnerable to backdoor attacks that compromise model reliability. This paper presents a comparative analysis of defense strategies against both classical and advanced backdoor attacks, evaluated across autoencoding and autoregressive models. Unlike prior studies, this work provides the first systematic comparison of perturbation-based, screening-based, and hybrid defenses in Transformer-based FL environments. Our results show that screening-based defenses consistently outperform perturbation-based ones, effectively neutralizing most attacks across architectures. However, this robustness comes with significant computational overhead, revealing a clear trade-off between security and efficiency. By explicitly identifying this trade-off, our study advances the understanding of defense strategies in federated learning and highlights the need for lightweight yet effective screening methods for trustworthy deployment in diverse application domains.},
DOI = {10.32604/cmes.2025.071190}
}