TY  - EJOU
AU  - Kim, Seunghan 
AU  - Lim, Changhoon 
AU  - Ryu, Gwonsang 
AU  - Kim, Hyunil 

TI  - How Robust Are Language Models against Backdoors in Federated Learning?
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2025
VL  - 145
IS  - 2
SN  - 1526-1506

AB  - 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.
KW  - Backdoor attack; federated learning; transformer-based language model; system robustness

DO  - 10.32604/cmes.2025.071190