Curriculum Vitae

Education

• North China University of Technology
  • Bachelor of Engineering
  • Mechanical Engineering, 2020 - 2021
  • Computer Science, 2021 - 2024
  • GPA: 3.75/4.0
• University of California, Riverside
  • Certificate in Graduate Preparation Program
  • Graduate Preparation Program in Engineering, 2023 - 2024

Publications

A Parallel Gannet Optimization Algorithm with Communication Strategies (PGOA)

Su, Jing-Bo, et al. "A Parallel Gannet Optimization Algorithm with Communication Strategies (PGOA)." International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Singapore: Springer Nature Singapore, 2022.

Enhancing Adversarial Attacks through Chain of Thought

Su, Jingbo. "Enhancing Adversarial Attacks through Chain of Thought." arXiv preprint arXiv:2410.21791 (2024).

Research Experience

• UC, Riverside Parallel Algorithm Lab with Prof. Yan Gu and Prof. Yihan Sun
• Project: ANNlib: Quickly Build-up Your Approximate Nearest Neighbor System
  • Reproduced Filtered and Stitched Vamana algorithms based on Microsoft’s Filtered-DiskANN research, integrating them into ANNlib using its components and ParlayLib’s parallel data structures
  • Acquired and prepared four million-scale vector datasets with natural and synthetic labels for comprehensive evaluation under various filtering constraints
  • Conducted detailed analysis and visualization of label distributions, selecting labels with different query difficulties to ensure robust algorithmic assessment
  • Reproduced baseline ANN systems and vector databases to enable direct performance comparisons, resolving environmental dependencies and configuration challenges
  • Visualization of experimental results demonstrated ANNlib’s ability to perform filtered approximate nearest neighbor problems with less indexing time, comparable accuracy, and higher throughput than original systems
• NCUT Evolutionary Computing Lab with Prof. Ruobin Wang and Dr. Lin Xu
• Project: A Parallel Gannet Optimization Algorithm with Communication Strategies (PGOA)
  • Presented final research findings at the 18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, substantially enhancing my communication skills and academic English proficiency
  • Carried out experiments with CEC-2013 to benchmark against the baseline Gannet Optimization Algorithm
  • Evaluated on both compact and parallel techniques. Experiential results demonstrated that the parallel strategy significantly surpassed the original GOA algorithm in computational efficiency and precision
  • Contributed to weekly lab meetings by conducting literature reviews on 10+ papers about Evolutionary Computing and presenting emerging concepts at graduate-level group discussions

Work Experience

• China National Investment & Guaranty Corporation
• Full-Stack Software Developer Intern
  • Applied full-stack development techniques by leveraging various frameworks (Django, React, SpringBoot) and refining programming skills in multiple languages (Python, TypeScript, Java)
  • Developed a project management system, using Django for backend and React for frontend, that significantly optimized project management processes and enhanced product managers’ efficiency
  • Independently built a script manager tool that empowered 20+ engineers to manage and execute Python scripts, contributing to streamlined script management and enhanced productivity across the team

Selected Projects

• UC, Riverside CS222 - Natural Language Processing
• Project: Enhancing Adversarial Attacks through Chain of Thought
  • Explored a novel attack method to raise success rates of adversarial attacks on large language models (LLMs)
  • Integrated chain-of-thought (CoT) prompting into a gradient-based adversarial attack on aligned LLMs and conducted experiments comparing performance on both baseline and Amazon’s auto-cot
  • Enhanced attack performance by improving LLM response logic through the intentional triggering of CoT reasoning
  • Forwarded the generated content to the Llama-Guard for objective assessment and evaluation of the various harmful types of ablation studies categorized by Llama-Guard
  • Experimental results demonstrated that the novel method successfully triggered the CoT ability on multiple aligned LLMs during attacks and outperformed prior approaches
• UC, Riverside CS178 - Project Sequence
• Project: MedShare: Healthcare Made Easy
  • As the team leader, communicated with my team members to determine the new features for our project. I also efficiently distributed resources to help co-workers who are behind the process to improve their development progress
  • With the popularity of large language models and chat agents, I integrated a chatbot by calling ChatGPT API to answer healthcare-related questions
  • A React-based user-friendly interface makes it easy for users to understand how to ask chatbot questions
  • The backend is developed in NodeJS; the chatbot is built on LangChain and utilizes retrieval augmented generation (RAG) in order to prevent the chatbot from confusing users when answering irrelevant questions
  • This trustworthy medical chatbot enhances the efficiency of patients’ access to healthcare knowledge, thus reducing delays when patients request to ask their doctors questions <!– * Built an easily-use medical management system with key features like messaging, forums, and appointment scheduling, integrating an API-callable chatbot to effectively enhance communication between doctors and patients and reduce healthcare delays.
  • Designed and implemented the frontend and backend of the system using ReactJS, NodeJS, and MongoDB. Employed GitHub to do version control for the project. Ensured efficient data management and a user-friendly interface.
  • Designing a chatbot system based on the LangChain framework and deploying it in a distributed manner with the Node system. Utilizing the Retrieval Augmented Generation (RAG) technique enables doctors to upload patient-related documents to flesh out the system knowledge base. –>

Teaching Experience

• Intermediate Data Structures and Algorithms (CS141), UCR, Grader, 2024
• Algorithmic Programming and Problem Solving (CS119L), UCR, Teaching Assistant, 2024

Community Involvements

• UCR Parllel Algorithm Lab, Riverside, Research Assistant, 2024 - 2025
• Weaviate: Certificate of AI in Prod, Seattle, 2024
• UIST 2024, Accessibility Guide Student Volunteer, Pittsburgh, 2024
• PPoPP/HPCA 2025, Student Volunteer, Las Vegas, 2025

Awards

• NCUT Scholarships, 2021 & 2022
• Silver medal in the 15th Programming Competition of NCUT, 2021
• Honorable Mention in the 46th ICPC Asia Regional Programming Contest, 2021