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

MadRadar: A Black-Box Physical Layer Attack Framework on mmWave...

David Hunt (Duke University), Kristen Angell (Duke University), Zhenzhou Qi (Duke University), Tingjun Chen (Duke University), Miroslav Pajic (Duke University)

Read More

The Advantages of Distributed TCAM Firewalls in Automotive Real-Time...

Evan Allen (Virginia Tech), Zeb Bowden (Virginia Tech Transportation Institute), J. Scot Ransbottom (Virginia Tech)

Read More

Efficient Normalized Reduction and Generation of Equivalent Multivariate Binary...

Arnau Gàmez-Montolio (City, University of London; Activision Research), Enric Florit (Universitat de Barcelona), Martin Brain (City, University of London), Jacob M. Howe (City, University of London)

Read More

ShapFuzz: Efficient Fuzzing via Shapley-Guided Byte Selection

Kunpeng Zhang (Shenzhen International Graduate School, Tsinghua University), Xiaogang Zhu (Swinburne University of Technology), Xi Xiao (Shenzhen International Graduate School, Tsinghua University), Minhui Xue (CSIRO's Data61), Chao Zhang (Tsinghua University), Sheng Wen (Swinburne University of Technology)

Read More