KHKeman Huang

Keman Huang

*This is an algorithmically generated author record based on publicly available information.

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


Keman Huang has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From Outcomes to Mechanisms: A Benchmark for Diagnosing LLM's Mechanism Hallucination on Data Inference Externalities

    by Xuanyi Li, Ankun Feng, Nianze Jing, Zeyan Li, Yaxin Li, Keman Huang, Xiaoyong Du

  • iRUC: Reducing Inter-Microservice Data Communication in Data-Intensive Systems via Unified Computation

    by Puwei Wang, Ruiheng Liu, Keman Huang, Xiaoyong Du

    In data-intensive microservice-based systems, frequent and large-scale inter-service communication poses a critical performance bottleneck, degrading throughput and escalating latency. Existing solutions exhibit notable limitations: microservice merging sacrifices loose coupling and system evolvability; resource-aware scheduling enhances communication efficiency but fails to reduce data volume; dynamic deployment reduces network distances while introducing compute-resource contention; and unnecessary data transfer elimination remains ineffective under massive data loads. Hence, to overcome these challenges, we propose iRUC, an approach for inter-service data communication Reduction via Unified Computation. In particular, we first design GraphQL+, an executable declarative language that extends GraphQL with service-interaction semantics to achieve unified, cross-language modeling of data processing and transmission across microservices. Second, we develop an LLM-based multi-agent system leveraging Claude 4.5 Sonnet and Gemini 2.5 Pro to automatically parse microservice code and synthesize corresponding GraphQL+ models. Third, we implement the unified execution engine for GraphQL+ models, including the database gateway that preserves microservice database autonomy while enabling cross-database queries. This design enables iRUC to perform the unified modeling and execution of data processing and transmission across microservices, thereby significantly reducing inter-service data transfer while maintaining microservice independence. Experimental evaluation on nine GitHub open-source microservice projects deployed on Huawei Cloud demonstrates iRUC’s effectiveness: compared with the unnecessary transfer elimination, dynamic deployment, and serverless computing approaches, iRUC improves throughput by 5.57×, 1.52×, and 1.87×, respectively, while reducing latency to 7.7%, 40.7%, and 37.4% of those approaches. These results show that iRUC achieves significant performance improvements in large-scale data processing scenarios.


  • From fear to act: enhancing older adults’ cybersecurity practices by elderly-oriented fear appeal messages design

    by Keman Huang, Xiaoqing Wang, Jilei Zhou, Bin Liang

    Purpose: As the cybersecurity risks rapidly grow for older adults, fear appeal – a persuasive message that highlights potential cyber threats to motivate protective behavior – has become increasingly prevalent in efforts to protect them. While numerous researchers have examined responses to fear appeals, no prior studies have implemented an actual fear appeal specifically targeting older adults to investigate its effectiveness in influencing their cybersecurity behaviors. Design/methodology/approach: Drawing on Protection Motivation Theory and the Elaboration Likelihood Model, we develop a framework that conceptualizes Family Risk Involvement (FRI) as a central cue, self-stigma perception as a peripheral cue, and cognitive age as a moderator. This framework explains how older adults process fear appeal messages to enhance their cybersecurity behaviors, including individual-level security policy compliance and collaborative security knowledge sharing. We operationalize the central and peripheral cues in the form of message designs integrated into elderly-oriented cybersecurity training materials. Using these materials, we conduct a large-scale study via an offline training program for 4,944 elderly participants from over 400 local communities across 14 provinces in China. Findings: Partial least squares structural equation modeling analysis of data collected from 4,944 participants reveals that the fear appeal message design through FRI and self-stigma perception significantly improves older adults’ cybersecurity behaviors. These effects are moderated by cognitive age, which exerts a reinforcement interaction effect. Originality/value: This study contributes to both the theoretical understanding and practical design of effective fear appeal messages to promote cybersecurity behaviors among older adults.


  • Open Access

    ISSF: An Intelligent Security Service Framework for Cloud-native Operations

    by Yikuan Yan, Keman Huang, Michael Siegel

    The growing system complexity of microservice architectures and the bilateral enhancement of artificial intelligence (AI) for both attackers and defenders present increasing security challenges for cloud-native operations. In particular, cloud-native operators require a holistic view of the dynamic security posture for the microservice-based cloud-native environment from a defense aspect. Additionally, both attackers and defenders can adopt advanced AI technologies. This makes the dynamic interaction and benchmark among different intelligent offense and defense strategies more crucial. Hence, following the multi-agent deep reinforcement learning (RL) paradigm, this research develops an agent-based intelligent security service framework (ISSF) for cloud-native operations. It includes a dynamic attack graph model to represent the cloud-native environment and an action model to represent offense and defense actions. Then we develop an approach to enable the training, publishing, and evaluating of intelligent security services using diverse deep RL algorithms and training strategies, facilitating their systematic development and benchmarking. The experiments demonstrate that our framework can sufficiently model the security posture of a cloud-native system for defenders, effectively develop and quantitatively benchmark different intelligent security services for both attackers and defenders, and guide further optimization.


  • Open Access

    Practically implementing an LLM-supported collaborative vulnerability remediation process: a team-based approach

    by Xiaoqing Wang, Yuanjing Tian, Keman Huang, Bin Liang

    Incorporating LLM into cybersecurity operations, a typical real-world high-stakes task, is critical but non-trivial in practice. Using cybersecurity as the study context, we conduct a three-step mix-method study to incorporate LLM into the vulnerability remediation process effectively. Specifically, we deconstruct the deficiencies in user satisfaction within the existing process (Study 1). This inspires us to design, implement, and empirically validate an LLM-supported collaborative vulnerability remediation process through a field study (Study 2). Given LLM's diverse contributions, we further investigate LLM's double-edge roles through the analysis of remediation reports and follow-up interviews (Study 3). In essence, our contribution lies in promoting an efficient LLM-supported collaborative vulnerability remediation process. These first-hand, real-world pieces of evidence suggest that when incorporating LLMs into practical processes, facilitating the collaborations among all associated stakeholders, reshaping LLMs' roles according to task complexity, as well as approaching the short-term side effects of improved user engagement facilitated by LLMs with a rational mindset.

  • Open Access

    ISSF: The Intelligent Security Service Framework for Cloud-Native Operation

    by Yikuan Yan, Keman Huang, Michael Siegel

    The growing system complexity from microservice architectures and the bilateral enhancement of artificial intelligence (AI) for both attackers and defenders presents increasing security challenges for cloud-native operations. In particular, cloud-native operators require a holistic view of the dynamic security posture for the cloud-native environment from a defense aspect. Additionally, both attackers and defenders can adopt advanced AI technologies. This makes the dynamic interaction and benchmark among different intelligent offense and defense strategies more crucial. Hence, following the multi-agent deep reinforcement learning (RL) paradigm, this research develops an agent-based intelligent security service framework (ISSF) for cloud-native operation. It includes a dynamic access graph model to represent the cloud-native environment and an action model to represent offense and defense actions. Then we develop an approach to enable the training, publishing, and evaluating of intelligent security services using diverse deep RL algorithms and training strategies, facilitating their systematic development and benchmark. The experiments demonstrate that our framework can sufficiently model the security posture of a cloud-native system for defenders, effectively develop and quantitatively benchmark different services for both attackers and defenders and guide further service optimization.

  • Open Access

    Public discourses and government interventions behind China’s ambitious carbon neutrality goal

    by Fang Zhang, Manchi Xu, Yikuan Yan, Keman Huang

    Mobilizing the public supports on ambitious climate change goals is crucial for climate action. Here we examine what public discourses have emerged in China around its ambitious carbon neutrality goal and how Chinese government has influenced its public opinion. By using deep learning model to analyze approximately one million microblogs from China, we track the evolution of seven climate discourses among the online public discussing China’s carbon neutrality goal, including scientific, moral, economic, co-benefit, energy security, political, and global frames. Among this community, we find a high level of supports towards China’s carbon neutrality goal. Opposers cite global and moral concerns as their main reason for opposition and are increasingly internally divided in China. Those who are neutral are more easily influenced by an economic discourse. Major climate policies are more effective than politics to influence public views on carbon neutrality.