Jingbo (Bob) Su

Jingbo (Bob) Su

CS PhD at William & Mary

Publications

ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

Published in The 2nd Workshop on Vector Databases (VecDB), 2026

ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems, based on popular graph-based ANNS algorithms.

Recommended citation: Shen, Zheqi, Jingbo Su, Zijin Wan, Yan Gu, and Yihan Sun. "ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search." arXiv preprint arXiv:2607.17582 (2026).

Enhancing Adversarial Attacks through Chain of Thought

Published in arXiv preprint, 2024

This paper enhances adversarial attacks on aligned LLMs by integrating chain of thought prompts with the greedy coordinate gradient technique, improving attack robustness and transferability, and evaluating harmful interactions using Llama Guard.

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

A Parallel Gannet Optimization Algorithm with Communication Strategies (PGOA)

Published in The 18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2023

Meta-heuristic algorithms have gained remarkable success in solving complex and large-scale problems. However, as the dimension of the problem increases, their elaborate implementations may lead to lower convergence speed and struggle with local optima easily. In this paper, a parallel Gannet Optimization Algorithm (GOA) with two novel communication strategies is proposed, and comparisons with the original GOA on 13 100-dimension benchmark functions are committed. Comprehensive experimental results indicate that the improved algorithm outperforms the original algorithm in not only better escaping local optima but also shorter running time.

Recommended citation: 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.