Xicong Shen

Xicong Shen

Auto-generated profile, based on publicly available information

Xicong Shen

College of Information Science and Electronic Engineering and the Zhejiang Key Laboratory of Information Processing, Communication and Networking, Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
23 June 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XSXicong Shen
Xicong Shen
YLYing Liu
Ying Liu
FLFu Li
Fu Li
CLChunguang Li
Chunguang Li
Federated learning (FL) has attracted widespread attention in the Internet of Things domain recently. With FL, multiple distributed devices can cooperatively train a global model by transmitting model updates without disclosing the original data. However, the distributed nature of FL makes it vulnerable to data poisoning attacks. In practice, malicious clients can launch the label-flipping attack (LFA) by simply tampering with the labels of local data, thus causing the global model to misclassify the samples of a selected class as the target class. Although some defense mechanisms have been proposed, they rely on specific assumptions about data distribution, and their performance degrades significantly when the data on clients are non-IID. Besides, most existing methods require clients to upload model updates in plaintext so that the server can identify and remove the malicious updates. But, direct transmission of model updates may still reveal private information. Considering these issues, we develop a label-flipping-robust and privacy-preserving FL (LFR-PPFL) algorithm, which is applicable to both independent and identically distributed (IID) and non-IID data. We first propose a detection method based on temporal analysis on cosine similarity to distinguish malicious clients from benign clients. Then, we propose a privacy-preserving computation protocol based on homomorphic encryption to implement this detection method and perform federated aggregation while protecting the privacy of clients. Besides, a detailed theoretical analysis is given to demonstrate the privacy guarantee of the proposed protocol. Experimental results on real-world data sets show that the proposed algorithm can effectively defend against LFAs under various data distributions.

4 November 2021 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
XSXicong Shen
Xicong Shen
YLYing Liu
Ying Liu
Distributed estimation over multitask networks, where the target parameter vectors (tasks) for different nodes can be different, has received much attention recently. In this article, we consider some practical application scenarios, where there are some similarities between tasks, and thus, intertask cooperation is beneficial to improve the estimation performance of nodes. In most of the existing multitask learning studies, local estimates are directly transmitted between neighboring nodes, and then, the adaptive combination strategy is adopted to achieve intertask cooperation. However, when the target parameter vectors contain sensitive information, direct transmission of local estimates may result in serious privacy breaches. To tackle this problem, we propose a privacy-preserving distributed multitask learning algorithm for collaborative estimation over networks. The proposed algorithm is implemented by a secure multiparty computation protocol designed on an organic combination of multiplicative/additive mask and additively homomorphic encryption technique. While allowing each node to adaptively cooperate with its neighbors, this protocol also preserves the privacy of the local estimates. Besides, we present a thorough privacy analysis of the proposed algorithm. Simulation results show that the proposed algorithm can effectively protect each node’s task against leakage without sacrificing the performance of estimation.

5 August 2019 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XSXicong Shen
Xicong Shen
YLYing Liu
Ying Liu
In the era of Big Data, as vast amounts of data are collected and shared among collaborators or uploaded to the Internet, the attacks on data privacy become more and more serious. Compressive privacy (CP) is a kind of privacy-preserving dimension-reduced projection schemes such that the projected data can be well used for the intended utility task but not for malicious applications. Nevertheless, most of existing CP approaches belong to centralized processing, which are not applicable to the cases that data is dispersedly collected/stored at distributed nodes and cannot be centralized to one node for processing due to various reasons. To tackle this problem, we propose a distributed differential utility/cost analysis (dDUCA), in which each node in the network is only allowed to exchange and combine the compressive-and-lossy projection matrix with its one-hop neighbors. Using the projection matrix, the classification of the projected data is performed. Experiments on several datasets confirm the effectiveness of the proposed method in terms of both privacy protection and utility retention.