Zhixiong Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhixiong Chen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Nianjun Zhou
IBM, Yorktown Height, NY, USA
2 shared publications - Tianyu Wang
Department of Computer Science, Pace University, New York, USA
2 shared publications - Hao Tang
University of Illinois
1 shared publication - Sui Song
New Jersey Institute of Technology, University Heights, Newark, NJ 07102 USA, phone:203-902-1498; fax: 203-902-1498
1 shared publication - Thomas S. Huang
UIUC
1 shared publication
Latest Publications
- Open Access
CyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education
Many non-traditional students in cybersecurity programs often lack access to advice from peers, family members and professors, which can hinder their educational experiences. Additionally, these students may not fully benefit from various LLM-powered AI assistants due to issues like content relevance, locality of advice, minimum expertise, and timing. This paper addresses these challenges by introducing an application designed to provide comprehensive support by answering questions related to knowledge, skills, and career preparation advice tailored to the needs of these students. We developed a learning tool platform, CyberMentor, to address the diverse needs and pain points of students majoring in cybersecurity. Powered by agentic workflow and Generative Large Language Models (LLMs), the platform leverages Retrieval-Augmented Generation (RAG) for accurate and contextually relevant information retrieval to achieve accessibility and personalization. We demonstrated its value in addressing knowledge requirements for cybersecurity education and for career marketability, in tackling skill requirements for analytical and programming assignments, and in delivering real time on demand learning support. Using three use scenarios, we showcased CyberMentor in facilitating knowledge acquisition and career preparation and providing seamless skill-based guidance and support. We also employed the LangChain prompt-based evaluation methodology to evaluate the platform's impact, confirming its strong performance in helpfulness, correctness, and completeness. These results underscore the system's ability to support students in developing practical cybersecurity skills while improving equity and sustainability within higher education. Furthermore, CyberMentor's open-source design allows for adaptation across other disciplines, fostering educational innovation and broadening its potential impact.
Open AccessCyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education
Many non-traditional students in cybersecurity programs often lack access to advice from peers, family members and professors, which can hinder their educational experiences. Additionally, these students may not fully benefit from various LLM-powered AI assistants due to issues like content relevance, locality of advice, minimum expertise, and timing. This paper addresses these challenges by introducing an application designed to provide comprehensive support by answering questions related to knowledge, skills, and career preparation advice tailored to the needs of these students. We developed a learning tool platform, CyberMentor, to address the diverse needs and pain points of students majoring in cybersecurity. Powered by agentic workflow and Generative Large Language Models (LLMs), the platform leverages Retrieval-Augmented Generation (RAG) for accurate and contextually relevant information retrieval to achieve accessibility and personalization. We demonstrated its value in addressing knowledge requirements for cybersecurity education and for career marketability, in tackling skill requirements for analytical and programming assignments, and in delivering real time on demand learning support. Using three use scenarios, we showcased CyberMentor in facilitating knowledge acquisition and career preparation and providing seamless skill-based guidance and support. We also employed the LangChain prompt-based evaluation methodology to evaluate the platform's impact, confirming its strong performance in helpfulness, correctness, and completeness. These results underscore the system's ability to support students in developing practical cybersecurity skills while improving equity and sustainability within higher education. Furthermore, CyberMentor's open-source design allows for adaptation across other disciplines, fostering educational innovation and broadening its potential impact.
- Open Access
Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation
Large language models (LLMs) and prompt engineering hold significant potential for advancing computer programming education through personalized instruction. This paper explores this potential by investigating three critical research questions: the systematic categorization of prompt engineering strategies tailored to diverse educational needs, the empowerment of LLMs to solve complex problems beyond their inherent capabilities, and the establishment of a robust framework for evaluating and implementing these strategies. Our methodology involves categorizing programming questions based on educational requirements, applying various prompt engineering strategies, and assessing the effectiveness of LLM-generated responses. Experiments with GPT-4, GPT-4o, Llama3-8b, and Mixtral-8x7b models on datasets such as LeetCode and USACO reveal that GPT-4o consistently outperforms others, particularly with the "multi-step" prompt strategy. The results show that tailored prompt strategies significantly enhance LLM performance, with specific strategies recommended for foundational learning, competition preparation, and advanced problem-solving. This study underscores the crucial role of prompt engineering in maximizing the educational benefits of LLMs. By systematically categorizing and testing these strategies, we provide a comprehensive framework for both educators and students to optimize LLM-based learning experiences. Future research should focus on refining these strategies and addressing current LLM limitations to further enhance educational outcomes in computer programming instruction.
Open AccessEnhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation
Large language models (LLMs) and prompt engineering hold significant potential for advancing computer programming education through personalized instruction. This paper explores this potential by investigating three critical research questions: the systematic categorization of prompt engineering strategies tailored to diverse educational needs, the empowerment of LLMs to solve complex problems beyond their inherent capabilities, and the establishment of a robust framework for evaluating and implementing these strategies. Our methodology involves categorizing programming questions based on educational requirements, applying various prompt engineering strategies, and assessing the effectiveness of LLM-generated responses. Experiments with GPT-4, GPT-4o, Llama3-8b, and Mixtral-8x7b models on datasets such as LeetCode and USACO reveal that GPT-4o consistently outperforms others, particularly with the "multi-step" prompt strategy. The results show that tailored prompt strategies significantly enhance LLM performance, with specific strategies recommended for foundational learning, competition preparation, and advanced problem-solving. This study underscores the crucial role of prompt engineering in maximizing the educational benefits of LLMs. By systematically categorizing and testing these strategies, we provide a comprehensive framework for both educators and students to optimize LLM-based learning experiences. Future research should focus on refining these strategies and addressing current LLM limitations to further enhance educational outcomes in computer programming instruction.
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 796-801
Comparison of Algorithms for Speaker Identification under Adverse Far-Field Recording Conditions with Extremely Short Utterances
In this paper, we compare the state-of-the-art algorithms for text-independent speaker identification under adverse far-field recording conditions with extremely short training and testing utterances. The algorithms include both the generative and discriminative methods. For the generative methods, three variants of the original Gaussian Mixture Model (GMM) and the Universal Background Model adapted Gaussian Mixture Model (UBM-GMM) are involved. For the discriminative methods, two kernel-based algorithms, namely, the Support Vector Machine (SVM) and the Relevance Vector Machine (RVM), are considered. The comparison mainly focuses on the speaker identification accuracy and the speed of the individual algorithms (for both training and testing) as well as the sparseness of the resulting model for the kernel-based methods. Finally, we demonstrate through experiments that multi-channel fusion of the far-field recordings yields improved performance across all the above algorithms.
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 796-801
Comparison of Algorithms for Speaker Identification under Adverse Far-Field Recording Conditions with Extremely Short Utterances
In this paper, we compare the state-of-the-art algorithms for text-independent speaker identification under adverse far-field recording conditions with extremely short training and testing utterances. The algorithms include both the generative and discriminative methods. For the generative methods, three variants of the original Gaussian Mixture Model (GMM) and the Universal Background Model adapted Gaussian Mixture Model (UBM-GMM) are involved. For the discriminative methods, two kernel-based algorithms, namely, the Support Vector Machine (SVM) and the Relevance Vector Machine (RVM), are considered. The comparison mainly focuses on the speaker identification accuracy and the speed of the individual algorithms (for both training and testing) as well as the sparseness of the resulting model for the kernel-based methods. Finally, we demonstrate through experiments that multi-channel fusion of the far-field recordings yields improved performance across all the above algorithms.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 596-601
Adaptive Network Flow Clustering
Flow level measurements are used to provide insights into the traffic flow crossing a network link. However, existing flow based network detection devices lack adaptive reconfigure functions when facing large number of flow sources such as spoofed attacks. The cache memory for storing flow records and the CPU for processing and/or exporting them could be increasing dramatically beyond what are available. The static sampling technique could not alleviate the issue totally. Instead it missed the ability to log accurately network traffic information. In this paper, we use Fuzzy Logic to achieve adaptive flow clustering. It reacts to the abrupt changes of flow numbers caused by flooding attack or any other attacks, and suggests a best clustering level. Therefore, large amount of flows are aggregated into a few flows in a real time. Our experiments demonstrate that the adaptive flow clustering prevents huge amount of malicious flows from exhausting memories and CPU resources while guarantees the legitimate flows.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 596-601
Adaptive Network Flow Clustering
Flow level measurements are used to provide insights into the traffic flow crossing a network link. However, existing flow based network detection devices lack adaptive reconfigure functions when facing large number of flow sources such as spoofed attacks. The cache memory for storing flow records and the CPU for processing and/or exporting them could be increasing dramatically beyond what are available. The static sampling technique could not alleviate the issue totally. Instead it missed the ability to log accurately network traffic information. In this paper, we use Fuzzy Logic to achieve adaptive flow clustering. It reacts to the abrupt changes of flow numbers caused by flooding attack or any other attacks, and suggests a best clustering level. Therefore, large amount of flows are aggregated into a few flows in a real time. Our experiments demonstrate that the adaptive flow clustering prevents huge amount of malicious flows from exhausting memories and CPU resources while guarantees the legitimate flows.