Changyu Dong

Changyu Dong

Auto-generated profile, based on publicly available information

Changyu Dong

Guangzhou University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
7 December 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
XGXiaojie Guo
Xiaojie Guo
Zheli LiuZheli Liu
Zheli Liu
JLJin Li
Jin Li
JGJiqiang Gao
Jiqiang Gao
BHBoyu Hou
Boyu Hou
Thar BakerThar Baker
Thar Baker
Federated learning (FL) enables a large number of clients to collaboratively train a global model through sharing their gradients in each synchronized epoch of local training. However, a centralized server used to aggregate these gradients can be compromised and forge the result in order to violate privacy or launch other attacks, which incurs the need to verify the integrity of aggregation. In this work, we explore how to design communication-efficient and fast verifiable aggregation in FL. We propose VeriFL, a verifiable aggregation protocol, with O(N) (dimension-independent) communication and O(N+d) computation for verification in each epoch, where N is the number of clients and d is the dimension of gradient vectors. Since d can be large in some real-world FL applications (e.g., 100K), our dimension-independent communication is especially desirable for clients with limited bandwidth and high-dimensional gradients. In addition, the proposed protocol can be used in the FL setting where secure aggregation is needed or there is a subset of clients dropping out of protocol execution. Experimental results indicate that our protocol is efficient in these settings.

2 April 2018 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XSXiangfu Song
Xiangfu Song
CDChangyu Dong
Changyu Dong
DYDandan Yuan
Dandan Yuan
QXQiu-Liang Xu
Qiu-Liang Xu
MZMinghao Zhao
Minghao Zhao
Recently, several practical attacks raised serious concerns over the security of searchable encryption. The attacks have brought emphasis on forward privacy, which is the key concept behind solutions to the adaptive leakage-exploiting attacks, and will very likely to become a must-have property of all new searchable encryption schemes. For a long time, forward privacy implies inefficiency and thus most existing searchable encryption schemes do not support it. Very recently, Bost (CCS 2016) showed that forward privacy can be obtained without inducing a large communication overhead. However, Bost's scheme is constructed with a relatively inefficient public key cryptographic primitive, and has poor I/O performance. Both of the deficiencies significantly hinder the practical efficiency of the scheme, and prevent it from scaling to large data settings. To address the problems, we first present FAST, which achieves forward privacy and the same communication efficiency as Bost's scheme, but uses only symmetric cryptographic primitives. We then present FASTIO, which retains all good properties of FAST, and further improves I/O efficiency. We implemented the two schemes and compared their performance with Bost's scheme. The experiment results show that both our schemes are highly efficient.

22 January 2019 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
JLJin Li
Jin Li
YHYanyu Huang
Yanyu Huang
YWYu Wei
Yu Wei
SLSiyi Lv
Siyi Lv
Zheli LiuZheli Liu
Zheli Liu
WLWenjing Lou
Wenjing Lou
Searchable symmetric encryption (SSE) has been widely applied in the encrypted database for queries in practice. Although SSE is powerful and feature-rich, it is always plagued by information leaks. Some recent attacks point out that forward privacy which disallows leakage from update operations, now becomes a basic requirement for any newly designed SSE schemes. However, the subsequent search operations can still leak a significant amount of information. To further strengthen security, we extend the definition of forward privacy and propose the notion of “forward search privacy”. Intuitively, it requires search operations over newly added documents do not leak any information about past queries. The enhanced security notion poses new challenges to the design of SSE. We address the challenges by developing the hidden pointer technique (HPT) and propose a new SSE scheme called Khons, which satisfies our security notion (with the original forward privacy notion) and is also efficient. We implemented Khons and our experiment results on large dataset (wikipedia) show that it is more efficient than existing SSE schemes with forward privacy.

14 April 2022 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
XMXu Ma
Xu Ma
XSXiaoqian Sun
Xiaoqian Sun
YWYuduo Wu
Yuduo Wu
Zheli LiuZheli Liu
Zheli Liu
XCXiaofeng Chen
Xiaofeng Chen
CDChangyu Dong
Changyu Dong
Federated learning is a collaborative machine learning framework where a global model is trained by different organizations under the privacy restrictions. Promising as it is, privacy and robustness issues emerge when an adversary attempts to infer the private information from the exchanged parameters or compromise the global model. Various protocols have been proposed to counter the security risks, however, it becomes challenging when one wants to make federated learning protocols robust against Byzantine adversaries while preserving the privacy of the individual participant. In this article, we propose a differentially private Byzantine-robust federated learning scheme (DPBFL) with high computation and communication efficiency. The proposed scheme is effective in preventing adversarial attacks launched by the Byzantine participants and achieves differential privacy through a novel aggregation protocol in the shuffle model. The theoretical analysis indicates that the proposed scheme converges to the approximate optimal solution with the learning error dependent on the differential privacy budget and the number of Byzantine participants. Experimental results on MNIST, FashionMNIST and CIFAR10 demonstrate that the proposed scheme is effective and efficient.

26 May 2017 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
AAAydin Abadi
Aydin Abadi
STSotirios Terzis
Sotirios Terzis
RMRoberto Metere
Roberto Metere
CDChangyu Dong
Changyu Dong
Private set intersection (PSI) is an essential cryptographic protocol that has many real world applications. As cloud computing power and popularity have been swiftly growing, it is now desirable to leverage the cloud to store private datasets and delegate PSI computation to it. Although a set of efficient PSI protocols have been designed, none support outsourcing of the datasets and the computation. In this paper, we propose two protocols for delegated PSI computation on outsourced private datasets. Our protocols have a unique combination of properties that make them particularly appealing for a cloud computing setting. Our first protocol, O-PSI, satisfies these properties by using additive homomorphic encryption and point-value polynomial representation of a set. Our second protocol, EO-PSI, is mainly based on a hash table and point-value polynomial representation and it does not require public key encryption; meanwhile, it retains all the desirable properties and is much more efficient than the first one. We also provide a formal security analysis of the two protocols in the semi-honest model and we analyze their performance utilizing prototype implementations we have developed. Our performance analysis shows that EO-PSI scales well and is also more efficient than similar state-of-the-art protocols for large set sizes.

10 November 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
LHLi Hu
Li Hu
AYAnli Yan
Anli Yan
HYHongyang Yan
Hongyang Yan
JLJin Li
Jin Li
THTeng Huang
Teng Huang
CYChunsheng Yang
Chunsheng Yang
Machine learning (ML) has gained widespread adoption in a variety of fields, including computer vision and natural language processing. However, ML models are vulnerable to membership inference attacks (MIAs), which can infer whether access data was used in training a target model, thus compromising the privacy of training data. This has led researchers to focus on protecting the privacy of ML. To date, although there have been extensive efforts to defend against MIAs, we still lack a comprehensive understanding of the progress made in this area, which can often impede our ability to design the most effective defense strategies. In this article, we aim to fill this critical knowledge gap by providing a systematic analysis of membership inference defense. Specifically, we classify and summarize the existing membership inference defense schemes, focusing on optimization phase and objective, basic intuition, and key technology, and we discuss possible research directions of membership inference defense in the future.