FedRand：透過隨機化LoRA子參數更新提升聯邦學習的隱私保護

摘要

聯邦學習（Federated Learning, FL）是一種廣泛應用於分散式模型訓練的框架，確保中央伺服器無法直接存取本地客戶端的數據。然而，這種方法可能仍無法完全保障數據隱私，因為在聚合過程中，本地客戶端的模型會暴露給中央伺服器。這一問題在利用FL訓練視覺語言模型（Vision-Language Models, VLMs）時尤為關鍵，因為VLMs容易記住訓練數據實例，使其易受成員推斷攻擊（Membership Inference Attacks, MIAs）的威脅。為應對這一挑戰，我們提出了FedRand框架，該框架避免披露完整的客戶端參數集。在此框架中，每個客戶端從伺服器隨機選取低秩適應（Low-Rank Adaptation, LoRA）的子參數，並將LoRA權重的其餘部分保留為私有參數。在客戶端私有數據集上訓練這兩類參數後，僅將非私有的客戶端參數回傳至伺服器進行聚合。此方法降低了客戶端VLM參數暴露的風險，從而增強了數據隱私。我們通過實驗驗證，與相關基線相比，FedRand在多個基準數據集上不僅提升了對MIAs的魯棒性，還達到了與傳輸完整LoRA參數方法相當的準確率。

English

Federated Learning (FL) is a widely used framework for training models in a decentralized manner, ensuring that the central server does not have direct access to data from local clients. However, this approach may still fail to fully preserve data privacy, as models from local clients are exposed to the central server during the aggregation process. This issue becomes even more critical when training vision-language models (VLMs) with FL, as VLMs can easily memorize training data instances, making them vulnerable to membership inference attacks (MIAs). To address this challenge, we propose the FedRand framework, which avoids disclosing the full set of client parameters. In this framework, each client randomly selects subparameters of Low-Rank Adaptation (LoRA) from the server and keeps the remaining counterparts of the LoRA weights as private parameters. After training both parameters on the client's private dataset, only the non-private client parameters are sent back to the server for aggregation. This approach mitigates the risk of exposing client-side VLM parameters, thereby enhancing data privacy. We empirically validate that FedRand improves robustness against MIAs compared to relevant baselines while achieving accuracy comparable to methods that communicate full LoRA parameters across several benchmark datasets.

FedRand：透過隨機化LoRA子參數更新提升聯邦學習的隱私保護

FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates

摘要

Summary

Support

Support