Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness
This work addresses the challenge of personalized adversarial robustness for edge computing clients, offering an incremental improvement over existing federated adversarial training methods.
The paper tackles the problem of limited personalization and high communication overhead in federated adversarial training for edge devices by proposing Lorica, a framework that achieves up to 68x improvements in communication efficiency and up to 29.9% and 52.2% enhancements in adversarial robustness and benign accuracy, respectively.
The growing use of large pre-trained models in edge computing has made model inference on mobile clients both feasible and popular. Yet these devices remain vulnerable to adversarial attacks, threatening model robustness and security. Federated adversarial training (FAT) offers a promising solution by enhancing robustness while preserving client privacy. However, FAT often yields a generalized global model that struggles with heterogeneous client data, leading to limited personalization and significant communication overhead. In this paper, we propose \textit{Lorica}, a personalized synergistic adversarial training framework that delivers customized defense models through a two-phase process. In Phase 1, \textit{Lorica} applies LoRA-FA for local adversarial fine-tuning, enabling personalized robustness while reducing communication by uploading only LoRA-FA parameters. In Phase 2, a forward-gating selection strategy improves benign accuracy, further refining the personalized model. This yields tailored defense models that effectively balance robustness and accuracy. Extensive experiments on benchmark datasets demonstrate that \textit{Lorica} can achieve up to 68$\times$ improvements in communication efficiency compared to state-of-the-art algorithms, while achieving up to 29.9\% and 52.2\% enhancements in adversarial robustness and benign accuracy, respectively.