Cheng Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Cheng Huang has a total of 115 co-authors. Here are the top co-authors by number of shared publications:
- Xuemin Shen
University of Waterloo
19 shared publications - Rongxing Lu
Faculty of Computer Science, University of New Brunswick, Fredericton, NB, Canada
18 shared publications - Dongxiao Liu
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
11 shared publications - Haiyong Bao
East China Normal University
9 shared publications - Anjia Yang
Jinan University
5 shared publications Bidi Ying
Huawei Technologies Canada, Ottawa, ON, Canada
5 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 23716-23732
GRANT: Privacy-Preserving Road Traffic Anomaly Detection Scheme Over Encrypted Data
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 23716-23732
GRANT: Privacy-Preserving Road Traffic Anomaly Detection Scheme Over Encrypted Data
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (6) , 12673-12686
TUBench: Benchmark Large Vision-Language Models on Trustworthiness With Unanswerable Questions
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (6) , 12673-12686
TUBench: Benchmark Large Vision-Language Models on Trustworthiness With Unanswerable Questions
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (19) , 45127-45140
FFHA: Fast and Full-Secure Handover Authentication With Prefilter-Then-Batch for Hybrid Blockchain-Enabled 6G-V2I
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (19) , 45127-45140
FFHA: Fast and Full-Secure Handover Authentication With Prefilter-Then-Batch for Hybrid Blockchain-Enabled 6G-V2I
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 5583-5596
Trigger as Entity: Backdoor Attacks to Graph-Based Retrieval-Augmented Generation of Large Language Models
Graph-based Retrieval-Augmented Generation (RAG) has achieved remarkable success in refining the outputs of Large Language Models (LLMs), enabling them to integrate relational and multi-hop knowledge into context-aware responses by constructing a knowledge graph from an external database. In this paper, we focus on the underexplored security risks arising from the external database, and propose the first backdoor attacks against the graph-based RAG of LLMs. Specifically, attackers insert the backdoor into the knowledge graph as entities by poisoning a carefully crafted corpus into the external database, thereby causing LLMs to output attacker-desired answers for trigger-containing queries while preserving correct answers for others. The attacks are formulated as a minimax problem, whose solution is a poison corpus. Powered by the chain-of-thought reasoning capabilities of LLMs, we propose a new strategy to solve the minimax problem. We craft retrieval text to insert triggers into the knowledge graph as entities, exploit hijacking text to redirect LLMs’ attention toward attacker-desired answers, and finally link the hijacking text to the triggers so that it serves as context only for trigger-containing queries. In addition, our attacks involve three types of triggers, including word-level, topic-level, and semantic-level, with progressively increasing stealthiness. Empirical results across multiple knowledge databases and language models indicate that the proposed attacks achieve the desired attack performance. Our findings highlight the substantial risks in LLM applications (e.g., chatbots and agents) built on graph-based RAG systems.
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 5583-5596
Trigger as Entity: Backdoor Attacks to Graph-Based Retrieval-Augmented Generation of Large Language Models
Graph-based Retrieval-Augmented Generation (RAG) has achieved remarkable success in refining the outputs of Large Language Models (LLMs), enabling them to integrate relational and multi-hop knowledge into context-aware responses by constructing a knowledge graph from an external database. In this paper, we focus on the underexplored security risks arising from the external database, and propose the first backdoor attacks against the graph-based RAG of LLMs. Specifically, attackers insert the backdoor into the knowledge graph as entities by poisoning a carefully crafted corpus into the external database, thereby causing LLMs to output attacker-desired answers for trigger-containing queries while preserving correct answers for others. The attacks are formulated as a minimax problem, whose solution is a poison corpus. Powered by the chain-of-thought reasoning capabilities of LLMs, we propose a new strategy to solve the minimax problem. We craft retrieval text to insert triggers into the knowledge graph as entities, exploit hijacking text to redirect LLMs’ attention toward attacker-desired answers, and finally link the hijacking text to the triggers so that it serves as context only for trigger-containing queries. In addition, our attacks involve three types of triggers, including word-level, topic-level, and semantic-level, with progressively increasing stealthiness. Empirical results across multiple knowledge databases and language models indicate that the proposed attacks achieve the desired attack performance. Our findings highlight the substantial risks in LLM applications (e.g., chatbots and agents) built on graph-based RAG systems.
- 20 May 2026
- Published by Elsevier in Information Sciences
- Vol. 753
CQED: Secure and efficient composite query processing over encrypted healthcare data
- 20 May 2026
- Published by Elsevier in Information Sciences
- Vol. 753
CQED: Secure and efficient composite query processing over encrypted healthcare data
- 2 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 27862-27876
AoI-Aware Privacy-Preserving Task Allocation in Vehicular Crowdsensing
In vehicular crowdsensing (VCS) systems, task allocation is a critical process that connects sensing demands with distributed vehicular resources. Its effectiveness fundamentally relies on optimizing the spatiotemporal features of vehicles, where information freshness is quantified by the Age of Information (AoI). However, task allocation that aims to jointly optimize spatial coverage and AoI requires the collection of precise trajectory and region data, which raises serious privacy concerns and becomes a key barrier to practical deployment. To achieve privacy-preserving and spatiotemporally optimized task allocation, this paper proposes a novel AoI-aware privacy-preserving task allocation framework based on secret sharing. The framework encodes both task regions and vehicle trajectories into timestamp-associated arrays and splits them into lightweight random shares. Through collaborative computation between two fog servers and a cloud platform, it enables secure evaluation of vehicle-task spatiotemporal matching without exposing the original data. Furthermore, we design a budget-constrained, spatiotemporally near-optimal vehicle selection algorithm that simultaneously maximizes spatial coverage and minimizes AoI under budget constraints. Security analysis and experimental results demonstrate that our scheme effectively protects location privacy while achieving near-optimal spatiotemporal coverage. Moreover, it significantly reduces both communication and computational overhead compared with a homomorphic encryption (HE) baseline, confirming its practical effectiveness for time-sensitive VCS applications.
- 2 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 27862-27876
AoI-Aware Privacy-Preserving Task Allocation in Vehicular Crowdsensing
In vehicular crowdsensing (VCS) systems, task allocation is a critical process that connects sensing demands with distributed vehicular resources. Its effectiveness fundamentally relies on optimizing the spatiotemporal features of vehicles, where information freshness is quantified by the Age of Information (AoI). However, task allocation that aims to jointly optimize spatial coverage and AoI requires the collection of precise trajectory and region data, which raises serious privacy concerns and becomes a key barrier to practical deployment. To achieve privacy-preserving and spatiotemporally optimized task allocation, this paper proposes a novel AoI-aware privacy-preserving task allocation framework based on secret sharing. The framework encodes both task regions and vehicle trajectories into timestamp-associated arrays and splits them into lightweight random shares. Through collaborative computation between two fog servers and a cloud platform, it enables secure evaluation of vehicle-task spatiotemporal matching without exposing the original data. Furthermore, we design a budget-constrained, spatiotemporally near-optimal vehicle selection algorithm that simultaneously maximizes spatial coverage and minimizes AoI under budget constraints. Security analysis and experimental results demonstrate that our scheme effectively protects location privacy while achieving near-optimal spatiotemporal coverage. Moreover, it significantly reduces both communication and computational overhead compared with a homomorphic encryption (HE) baseline, confirming its practical effectiveness for time-sensitive VCS applications.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 4621-4636
Region Partitioning-Based Scalable Real-Time Network Verification via Native Distributed Architecture
Data plane verification (DPV) is critical in ensuring correct network operation, but practical deployment demands solutions that simultaneously achieve real-time responsiveness and massive scalability. Conventional centralized DPV approaches fundamentally struggle with these requirements due to inherent architectural constraints: the single verification server becomes both a computational bottleneck during rapid verification cycles and a collection bottleneck when gathering real-time data plane updates across large-scale networks. As network scale increases, these limitations manifest as either unacceptable verification latency or incomplete data plane visibility—precisely when robust DPV is essential for preventing packet loss and security violations. This paper introduces Atlas*, a novel distributed data plane verification (DPV) system designed to address fundamental scalability and real-time performance challenges in network verification. Atlas* achieves this through a hierarchical architecture that strategically distributes verification tasks across specialized components, combined with innovative parallel processing techniques to maximize computational efficiency. Simultaneously, Atlas* optimizes communication latency between distributed components through a region partitioning algorithm. Extensive evaluations in simulated environments and production deployments demonstrate Atlas*’s capability to perform fast, scalable verification while maintaining lightweight resource allocation. Empirical results show Atlas* achieves 2-7x speedup compared to existing state-of-the-art solutions, with performance advantages progressively increasing as network scale expands.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 4621-4636
Region Partitioning-Based Scalable Real-Time Network Verification via Native Distributed Architecture
Data plane verification (DPV) is critical in ensuring correct network operation, but practical deployment demands solutions that simultaneously achieve real-time responsiveness and massive scalability. Conventional centralized DPV approaches fundamentally struggle with these requirements due to inherent architectural constraints: the single verification server becomes both a computational bottleneck during rapid verification cycles and a collection bottleneck when gathering real-time data plane updates across large-scale networks. As network scale increases, these limitations manifest as either unacceptable verification latency or incomplete data plane visibility—precisely when robust DPV is essential for preventing packet loss and security violations. This paper introduces Atlas*, a novel distributed data plane verification (DPV) system designed to address fundamental scalability and real-time performance challenges in network verification. Atlas* achieves this through a hierarchical architecture that strategically distributes verification tasks across specialized components, combined with innovative parallel processing techniques to maximize computational efficiency. Simultaneously, Atlas* optimizes communication latency between distributed components through a region partitioning algorithm. Extensive evaluations in simulated environments and production deployments demonstrate Atlas*’s capability to perform fast, scalable verification while maintaining lightweight resource allocation. Empirical results show Atlas* achieves 2-7x speedup compared to existing state-of-the-art solutions, with performance advantages progressively increasing as network scale expands.
- 30 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 4861-4876
KDCS: Achieving Efficient and Privacy-Preserving ($k,d$k,d)-Truss Community Search for Social Networks
Community search is essential in social network analysis, with the ($k,d$)-truss model offering a robust framework to identify densely connected subgraphs that contain a query vertex and meet both $k$-truss and distance constraints. Despite the increasing reliance on cloud servers for processing large social network graph data, privacy concerns remain unaddressed. To fill this gap, we propose a novel privacy-preserving ($k,d$)-truss community search (KDCS) scheme based on weighted community graphs. Specifically, to enhance search efficiency, we introduce a $k$-truss-G (KTG) tree to index communities for efficient queries. Firstly, we develop a boundary vertex encoding mechanism for the social distance matrix. Then, we design a KTG tree construction algorithm and a ($k,d$)-truss community search algorithm based on the concept of segmentation and assembly. To ensure data security, we propose a secure community distance calculation (SCDC) algorithm, which utilizes mutually orthogonal matrices to preserve the privacy of the social distance matrix while accurately calculating the social distance. Furthermore, improved symmetric homomorphic encryption (iSHE) and matrix encryption are utilized to safeguard both dataset privacy and query privacy effectively. In addition, rigorous security analysis demonstrates that the proposed KDCS scheme is indeed privacy-preserving. Finally, extensive comparative experiments with real social network datasets show that KDCS exhibits outstanding performance at every stage, underscoring its practical significance.
- 30 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 4861-4876
KDCS: Achieving Efficient and Privacy-Preserving ($k,d$k,d)-Truss Community Search for Social Networks
Community search is essential in social network analysis, with the ($k,d$)-truss model offering a robust framework to identify densely connected subgraphs that contain a query vertex and meet both $k$-truss and distance constraints. Despite the increasing reliance on cloud servers for processing large social network graph data, privacy concerns remain unaddressed. To fill this gap, we propose a novel privacy-preserving ($k,d$)-truss community search (KDCS) scheme based on weighted community graphs. Specifically, to enhance search efficiency, we introduce a $k$-truss-G (KTG) tree to index communities for efficient queries. Firstly, we develop a boundary vertex encoding mechanism for the social distance matrix. Then, we design a KTG tree construction algorithm and a ($k,d$)-truss community search algorithm based on the concept of segmentation and assembly. To ensure data security, we propose a secure community distance calculation (SCDC) algorithm, which utilizes mutually orthogonal matrices to preserve the privacy of the social distance matrix while accurately calculating the social distance. Furthermore, improved symmetric homomorphic encryption (iSHE) and matrix encryption are utilized to safeguard both dataset privacy and query privacy effectively. In addition, rigorous security analysis demonstrates that the proposed KDCS scheme is indeed privacy-preserving. Finally, extensive comparative experiments with real social network datasets show that KDCS exhibits outstanding performance at every stage, underscoring its practical significance.