21 papers
DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection
Junyu Ren, Xingjian Pan, Wensheng Gan +1
Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such a…
UPER: Efficient Utility-driven Partially-ordered Episode Rule Mining
Hong Lin, Wensheng Gan, Junyu Ren +1
Episode mining is a fundamental problem in analyzing a sequence of numerous events. For discovering strong relationships between events in a complex event sequence, episode rule mi…
Guided Exploration of Sequential Rules
Wensheng Gan, Gengsen Huang, Junyu Ren +1
In pattern mining, sequential rules provide a formal framework to capture the temporal relationships and inferential dependencies between items. However, the discovery process is c…
High-utility Sequential Rule Mining Utilizing Segmentation Guided by Confidence
Chunkai Zhang, Jiarui Deng, Maohua Lyu +2
Within the domain of data mining, one critical objective is the discovery of sequential rules with high utility. The goal is to discover sequential rules that exhibit both high uti…
Discovering High-utility Sequential Rules with Increasing Utility Ratio
Zhenqiang Ye, Wensheng Gan, Gengsen Huang +2
Utility-driven mining is an essential task in data science, as it can provide deeper insight into the real world. High-utility sequential rule mining (HUSRM) aims at discovering se…
Enhancing Temporal Awareness in LLMs for Temporal Point Processes
Lili Chen, Wensheng Gan, Shuang Liang +1
Temporal point processes (TPPs) are crucial for analyzing events over time and are widely used in fields such as finance, healthcare, and social systems. These processes are partic…