Cheng Huang

Dr. Cheng Huang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZLZhiqiang Li
Zhiqiang Li
HBHaiyong Bao
Haiyong Bao
MGMenghong Guan
Menghong Guan
HPHao Pan
Hao Pan
CHCheng Huang
Cheng Huang
Hong-Ning DaiHong-Ning Dai
Hong-Ning Dai
Despite federated learning (FL)'s potential in collaborative learning, its performance has deteriorated due to the data heterogeneity of distributed users. Recently, clustered federated learning (CFL) has emerged to address this challenge by partitioning users into clusters according to their similarity. However, CFL faces difficulties in training when users are unwilling to share their cluster identities due to privacy concerns. To address these issues, we present an innovative Efficient and Robust Secure Aggregation scheme for CFL, dubbed EBS-CFL. The proposed EBS-CFL supports effectively training CFL while maintaining users' cluster identity confidentially. Moreover, it detects potential poisonous attacks without compromising individual client gradients by discarding negatively correlated gradients and aggregating positively correlated ones using a weighted approach. The server also authenticates correct gradient encoding by clients. EBS-CFL has high efficiency with client-side overhead O(ml + m^2) for communication and O(m^2l) for computation, where m is the number of cluster identities, and l is the gradient size. When m = 1, EBS-CFL's computational efficiency of client is at least O(log(n)) times better than comparison schemes, where n is the number of clients. In addition, we validate the scheme through extensive experiments. Finally, we theoretically prove the scheme's security.

15 August 2026 in Peer-to-Peer Networking and Applications
Verified
Journal Article
Open access
PDF file
JHJialu Hao
Jialu Hao
LNLin Ni
Lin Ni
WDWei Dai
Wei Dai
BWBo Wu
Bo Wu
CHCheng Huang
Cheng Huang
Attribute-based encryption (ABE) is a promising primitive to protect data privacy and achieve flexible data sharing. Considering the increasing number of resource-limited devices in the Internet of Things (IoT) era, outsourcing the expensive decryption operations of ABE to a powerful proxy is helpful and necessary for users. However, the innate distrust between the user and the proxy makes security and fairness challenging. That is, the user would worry about whether the proxy executes the outsourced decryption honestly without breaking data confidentiality. Conversely, the proxy may be concerned that if she can get the deserved reward as promised. In this paper, we propose a blockchain-based scheme to provide secure and fair outsourced decryption service of attribute-based ciphertext. Specifically, we propose an efficient attribute-based encryption scheme with verifiable outsourced decryption (ABE-VOD), which enables the user to outsource most of the decryption operations securely and verify the returned result with little cost. We then integrate blockchain into ABE-VOD to manage the outsourced decryption tasks and deal with the reward and punishment issues as a trusted mediator, which could effectively guarantee fairness. Finally, we implement a proof-of-concept prototype on a local Ethereum testnet to evaluate the feasibility and performance of the proposed scheme.

13 August 2026
Verified
Book Chapter
Closed access
PDF file
YZYunlei Zhao
Yunlei Zhao
BZBiming Zhou
Biming Zhou
ZZZhixiang Zhao
Zhixiang Zhao
YDYifan Dong
Yifan Dong
CHCheng Huang
Cheng Huang
HJHaodong Jiang
Haodong Jiang


21 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
JGJi Guo
Ji Guo
XWXiaolei Wen
Xiaolei Wen
WJWenbo Jiang
Wenbo Jiang
CHCheng Huang
Cheng Huang
JLJinjin Li
Jinjin Li
HLHongwei Li
Hongwei Li
With the widespread application of super-resolution (SR) in various fields, researchers have begun to investigate its security. Previous studies have demonstrated that SR models can also be subjected to backdoor attacks through data poisoning, affecting downstream tasks. A backdoor SR model generates an attacker-predefined target image when given a triggered image while producing a normal high-resolution (HR) output for clean images. However, prior backdoor attacks on SR models have primarily focused on the stealthiness of poisoned low-resolution (LR) images while ignoring the stealthiness of poisoned HR images, making it easy for users to detect anomalous data. To address this problem, we propose BadSR, which improves the stealthiness of poisoned HR images. The key idea of BadSR is to approximate the clean HR image and the pre-defined target image in the feature space while ensuring that modifications to the clean HR image remain within a constrained range. The poisoned HR images generated by BadSR can be integrated with existing triggers. To further improve the effectiveness of BadSR, we design an adversarially optimized trigger and a backdoor gradient-driven poisoned sample selection method based on a genetic algorithm. The experimental results show that BadSR achieves a high attack success rate in various models and data sets, significantly affecting downstream tasks.

21 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
XHXinyu Huang
Xinyu Huang
SHShisheng Hu
Shisheng Hu
MLMushu Li
Mushu Li
CHCheng Huang
Cheng Huang
XSXuemin Shen
Xuemin Shen
In this paper, we propose a novel efficient digital twin (DT) data processing scheme to reduce service latency for multicast short video streaming. Particularly, DT is constructed to emulate and analyze user status for multicast group update and swipe feature abstraction. Then, a precise measurement model of DT data processing is developed to characterize the relationship among DT model size, user dynamics, and user clustering accuracy. A service latency model, consisting of DT data processing delay, video transcoding delay, and multicast transmission delay, is constructed by incorporating the impact of user clustering accuracy. Finally, a joint optimization problem of DT model size selection and bandwidth allocation is formulated to minimize the service latency. To efficiently solve this problem, a diffusion-based resource management algorithm is proposed, which utilizes the denoising technique to improve the action-generation process in the deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed DT data processing scheme outperforms benchmark schemes in terms of service latency.