Hao Zhou

Hao Zhou

Auto-generated profile, based on publicly available information

Hao Zhou

School of Computer Science, Nanjing University of Post and Telecommunication, the State Key Laboratory of Tibetan Intelligence, Nanjing University, Nanjing, 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
11 May 2022 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
GYGeng Yang
Geng Yang
HDHua Dai
Hua Dai
GLGuoxiu Liu
Guoxiu Liu
Federated learning (FL) can protect clients’ privacy from leakage in distributed machine learning. Applying federated learning to edge computing can protect the privacy of edge clients and benefit edge computing. Nevertheless, eavesdroppers can analyze the parameter information to specify clients’ private information and model features. And it is difficult to achieve a high privacy level, convergence, and low communication overhead during the entire process in the FL framework. In this paper, we propose a novel privacy-preserving federated learning framework for edge computing (PFLF). In PFLF, each client and the application server add noise before sending the data. To protect the privacy of clients, we design a flexible arrangement mechanism to count the optimal training times for clients. We prove that PFLF guarantees the privacy of clients and servers during the entire training process. Then, we theoretically prove that PFLF has three main properties: 1) For a given privacy level and model aggregation times, there is an optimal number of participating times for clients; 2) There is an upper and lower bound of convergence; 3) PFLF achieves low communication overhead by designing a flexible participation training mechanism. Simulation experiments confirm the correctness of our theoretical analysis. Therefore, PFLF helps design a framework to balance privacy levels and convergence and achieve low communication overhead when there is a part of clients dropping out of training.

7 December 2022 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
GYGeng Yang
Geng Yang
YHYuxian Huang
Yuxian Huang
HDHua Dai
Hua Dai
YXYang Xiang
Yang Xiang
In federated learning (FL), each client collaboratively trains the global model through the cloud server (CS) without sharing its original dataset in edge computing. However, CS can analyze and forge the uploaded parameters and infer the privacy of clients, which calls for the necessity of verifying the integrity and protecting the privacy for aggregation. Although there are some works to ensure the verifiability of aggregation results, there is still a lack of work on analyzing the relationship between verification and dropout rate for edge computing. In this work, we propose privacy-preserving and verifiable federated learning (PVFL) with low communication and computation overhead for verification. We theoretically demonstrate that PVFL has three properties: 1) the communication overhead for verification is independent of the dropouts and the dimension of the parameter vector; 2) the computation overhead for verification is independent of the dropouts; 3) the value of the loss function is negatively correlated with the number of dropouts. Experimental results demonstrate the correctness of our theoretical results and practical performance with a high dropout rate, thereby facilitating the design of privacy-preserving and verifiable FL algorithms for edge computing with a high dimension of parameter vectors and a high dropout rate.

29 December 2021 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
GYGeng Yang
Geng Yang
YXYang Xiang
Yang Xiang
YBYunlu Bai
Yunlu Bai
WWWeiya Wang
Weiya Wang
The proliferation of various items recommended by Internet-based systems has resulted in the exponential growth of the number of ratings in the big data era. Recent advances in matrix factorization have made it an effective way to process these ratings for recommendations. However, we confront a challenge in deploying a matrix factorization model for recommendations in big data that arises from the typically resource-constrained local devices regarding their storage space and computing capacity. This paper proposes a novel lightweight matrix factorization for recommendations. Our scheme deploys shard grandients training on user local internet of things(IoT) devices, which makes it possible for users to train big data model locally. We design a two-phase solution to protect the security of users’ data and reduce the dimension of the items. Moreover, we optimize the proposed scheme by introducing a stabilization mechanism to decrease the scale of the perturbed gradients. Some experimental results are given with two real online datasets, MovieLens and LibimSeTi. The theoretical analysis and experimental results demonstrate that compared with other methods, the proposed scheme achieves a good performance in terms of security, accuracy, and efficiency.

7 May 2025 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
HDHua Dai
Hua Dai
GYGeng Yang
Geng Yang
YXYang Xiang
Yang Xiang
Federated Learning (FL) has emerged as a key enabler of privacy-preserving distributed model training in edge computing environments, crucial for service-oriented applications such as personalized healthcare, smart cities, and intelligent assistants. However, existing privacy-preserving FL methods are susceptible to multiple privacy leakage attacks (MPLA), where adversaries infer sensitive information through repeated gradient updates. This paper proposes a Robust and Communication-Efficient Federated Learning (RCFL) framework designed to enhance privacy protection and communication efficiency in edge-based service environments. RCFL integrates a global privacy-preserving mechanism with an innovative privacy encoding strategy that minimizes privacy risks over multiple data releases while significantly reducing communication overhead. The proposed framework's theoretical analysis demonstrates its ability to maintain differential privacy across numerous interactions, ensuring robust model convergence and efficiency. Experimental results using MNIST and CIFAR-10 datasets reveal that RCFL can lower the MPLA success rate from 88.56% to 42.57% compared to state-of-the-art methods, while reducing communication costs by over 90%. These findings underscore RCFL's potential to enhance security, efficiency, and scalability in service-oriented edge computing applications.

6 January 2026 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
HDHua Dai
Hua Dai
GYGeng Yang
Geng Yang
YXYang Xiang
Yang Xiang
Federated learning (FL) is a key paradigm for deploying AI models across large numbers of Internet of Things (IoT) devices in edge computing. While FL avoids uploading raw data to a central server, client privacy remains vulnerable during new client integration, when previously unseen devices first register their identities and cryptographic keys. A malicious or semi-honest central server (CS) can manipulate training to isolate target gradients, reconstruct local data, and tamper with aggregation. We study the Identity Forgery and Gradient Inversion Attack (IFGIA) against federated edge learning. By fabricating virtual clients and exploiting secure aggregation, a malicious CS can recover target gradients with success rates above 99.5% under realistic edge settings, revealing a critical weakness in existing privacy-preserving and verifiable FL schemes. To defend against IFGIA, we propose Robust Federated Learning (RFL), a framework tailored for edge computing that combines model splitting between edge clients and edge servers, lightweight differential privacy on intermediate representations, and split verification using digital signatures and homomorphic hashes. Experiments show that RFL reduces IFGIA's success rate to 73.6%, shrinks per-client communication from 375 MB to 40 KB, accelerates edge-side training by at least 10×, and maintains competitive accuracy.