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

Towards generic backward-compatible software upgrades for COSPAS-SARSAT EPIRB 406...

Ahsan Saleem (University of Jyväskylä, Finland), Andrei Costin (University of Jyväskylä, Finland), Hannu Turtiainen (University of Jyväskylä, Finland), Timo Hämäläinen (University of Jyväskylä, Finland)

Read More

WIP: Adversarial Object-Evasion Attack Detection in Autonomous Driving Contexts:...

Rao Li (The Pennsylvania State University), Shih-Chieh Dai (Pennsylvania State University), Aiping Xiong (Penn State University)

Read More

A Security and Usability Analysis of Local Attacks Against...

Tarun Kumar Yadav (Brigham Young University), Kent Seamons (Brigham Young University)

Read More

Architecting Trigger-Action Platforms for Security, Performance and Functionality

Deepak Sirone Jegan (University of Wisconsin-Madison), Michael Swift (University of Wisconsin-Madison), Earlence Fernandes (University of California San Diego)

Read More