Linghui Zhu

Linghui Zhu

Auto-generated profile, based on publicly available information

Linghui Zhu

Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LZLinghui Zhu
Linghui Zhu
XLXinyi Liu
Xinyi Liu
YLYiming Li
Yiming Li
XYXue Yang
Xue Yang
Shu-Tao XiaShu-Tao Xia
Shu-Tao Xia
RLRongxing Lu
Rongxing Lu
Federated learning (FL) enables data owners to train a global model with shared gradients while keeping private training data locally. However, recent research demonstrated that the adversary may infer private training data of clients from the exchanged local gradients, e.g., having deep leakage from gradients (DLGs). Many existing privacy-preserving approaches take usage of differential privacy (DP) to guarantee privacy. Nevertheless, the widely used privacy budget of DP (e.g., evenly distribution) leads to a sharp decline of model accuracy. To improve the model accuracy, some schemes only consider allocating the privacy budget to the fully connected layers. However, we reveal that the adversary may still reconstruct the private training data by adopting the DLG attack with the gradients of convolutional layers. In this article, we propose a fine-grained DP federated learning (DPFL) scheme, which guarantees privacy and remains high model performance simultaneously. Specifically, inspired by the methods that measure the importance of layers in deep learning, we propose a fine-grained method to allocate noise according to the importance value of layers in order to remain high model performance. Besides, we combine an active client selection strategy with DPFL and perform fine-tuning with a public data set on the server to further ensure the model performance. We evaluate DPFL under both independent and identically distributed (i.i.d) and non-i.i.d data settings to show that our method can achieve similar accuracy as the plain FL (e.g., FedAvg). We also demonstrate that our DPFL can resist the DLG attack to verify its privacy guarantee.

27 February 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYiming Li
Yiming Li
LZLinghui Zhu
Linghui Zhu
XJXiaojun Jia
Xiaojun Jia
YBYang Bai
Yang Bai
YJYong Jiang
Yong Jiang
KRKui Ren
Kui Ren
Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property for its owner. However, recent studies revealed the threats of model stealing, where the adversaries can obtain a function-similar copy of the victim model, even when they can only query the model. In this paper, we propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously, without introducing new security risks. In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by modifying a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. In particular, we develop our MOVE method under both glass-boxand closed-box settings and analyze its theoretical foundation to provide comprehensive model protection. Extensive experiments on benchmark datasets verify the effectiveness of our method and its resistance to potential adaptive attacks.

28 November 2022
Verified
Book Chapter
Closed access
PDF file
YLYiming Li
Yiming Li
LZLinghui Zhu
Linghui Zhu
YBYang Bai
Yang Bai
YJYong Jiang
Yong Jiang
Shu-Tao XiaShu-Tao Xia
Shu-Tao Xia