Weiheng Bai (University of Minnesota), Qiushi Wu (IBM Research), Kefu Wu, Kangjie Lu (University of Minnesota)

In recent years, large language models (LLMs) have been widely used in security-related tasks, such as security bug identification and patch analysis. The effectiveness of LLMs in these tasks is often influenced by the construction of appropriate prompts. Some state-of-the-art research has proposed multiple factors to improve the effectiveness of building prompts. However, the influence of prompt content on the accuracy and efficacy of LLMs in executing security tasks remains underexplored. Addressing this gap, our study conducts a comprehensive experiment, assessing various prompt methodologies in the context of security-related tasks. We employ diverse prompt structures and contents and evaluate their impact on the performance of LLMs in security-related tasks. Our findings suggest that appropriately modifying prompt structures and content can significantly enhance the performance of LLMs in specific security tasks. Conversely, improper prompt methods can markedly reduce LLM effectiveness. This research not only contributes to the understanding of prompt influence on LLMs but also serves as a valuable guide for future studies on prompt optimization for security tasks. Our code and dataset is available at Wayne-Bai/Prompt-Affection.

View More Papers

Certificate Transparency Revisited: The Public Inspections on Third-party Monitors

Aozhuo Sun (Institute of Information Engineering, Chinese Academy of Sciences), Jingqiang Lin (School of Cyber Science and Technology, University of Science and Technology of China), Wei Wang (Institute of Information Engineering, Chinese Academy of Sciences), Zeyan Liu (The University of Kansas), Bingyu Li (School of Cyber Science and Technology, Beihang University), Shushang Wen (School of…

Read More

Group-based Robustness: A General Framework for Customized Robustness in...

Weiran Lin (Carnegie Mellon University), Keane Lucas (Carnegie Mellon University), Neo Eyal (Tel Aviv University), Lujo Bauer (Carnegie Mellon University), Michael K. Reiter (Duke University), Mahmood Sharif (Tel Aviv University)

Read More

Secret-Shared Shuffle with Malicious Security

Xiangfu Song (National University of Singapore), Dong Yin (Ant Group), Jianli Bai (The University of Auckland), Changyu Dong (Guangzhou University), Ee-Chien Chang (National University of Singapore)

Read More