With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) have received considerable attention due to their stunning intelligence, and some studies consider using ChatGPT for vulnerability detection. However, they do not fully consider the characteristics of LLMs, since their designed questions to ChatGPT are simple without a prompt design tailored for vulnerability detection. This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs. Firstly, we complement previous work by applying various improvements to the basic prompt. Moreover, we incorporate structural and sequential auxiliary information to improve the prompt design. Moreover, we leverage ChatGPT’s ability of memorizing multi-round dialogue to design suitable prompts for vulnerability detection. We conduct extensive experiments on two vulnerability datasets to demonstrate the effectiveness of prompt-enhanced vulnerability detection using ChatGPT.
Wed 17 AprDisplayed time zone: Lisbon change
10:30 - 11:00 | |||
10:30 30mPoster | KareCoder: A New Knowledge-Enriched Code Generation System Posters Tao Huang Shandong Normal University, Zhihong Sun Shandong Normal University, Zhi Jin Peking University, Ge Li Peking University, Chen Lyu Shandong Normal University | ||
10:30 30mPoster | An Empirical Study on Cross-language Clone Bugs Posters Honghao Chen Shanghai Jiao Tong University, Ye Tang Shanghai Jiao Tong University, Hao Zhong Shanghai Jiao Tong University | ||
10:30 30mPoster | Poster: Kotlin Assimilating the Android Ecosystem - An Appraisal of Diffusion and Impact on Maintainability Posters Riccardo Coppola Politecnico di Torino, Tommaso Fulcini Politecnico di Torino, Marco Torchiano Politecnico di Torino | ||
10:30 30mPoster | Prompt-Enhanced Software Vulnerability Detection Using ChatGPT Posters Chenyuan Zhang Xiamen University, Hao Liu Xiamen University, Jiutian Zeng Alibaba, Kejing Yang Alibaba, Yuhong Li Alibaba, Hui Li Xiamen University Pre-print | ||
10:30 30mPoster | Applying Transformer Models for Automatic Build Errors Classification of Java-Based Open Source Projects Posters Jonathan Lee National Taiwan University, Mason Li National Taiwan University, Kuo-Hsun Hsu Department of Computer Science, National Taichung University of Education | ||
10:30 30mPoster | A First Look at the General Data Protection Regulation (GDPR) in Open-Source Software Posters Lucas Franke Virginia Tech, Huayu Liang Virginia Tech, Aaron Brantly Virginia Tech, James C. Davis Purdue University, Chris Brown Virginia Tech | ||
10:30 30mPoster | Interpretable Software Maintenance and Support Effort Prediction Using Machine Learning Posters Media Attached | ||
10:30 30mPoster | Endogeneity, Instruments, and Two-Stage Models Posters | ||
10:30 30mPoster | ParSE: Efficient Detection of Smart Contract Vulnerabilities via Parallel and Simplified Symbolic Execution Posters | ||
10:30 30mPoster | Safety Monitoring of Deep Reinforcement Learning Agents Posters Amirhossein Zolfagharian University of Ottawa - School of Electrical Engineering & Computer Science (EECS), Manel Abdellatif Software and Information Technology Engineering Department, École de Technologie Supérieure, Lionel Briand University of Ottawa, Canada; Lero centre, University of Limerick, Ireland, Ramesh S | ||
10:30 30mPoster | An Actionable Framework for Understanding and Improving Talent Retention as a Competitive Advantage in IT Organizations Posters Luiz Alexandre Costa UNIRIO, Edson Dias Federal University of Pará, Danilo Ribeiro Zup Innovation, Awdren Fontão Federal University of Mato Grosso do Sul (UFMS), Gustavo Pinto Federal University of Pará (UFPA) and Zup Innovation, Rodrigo Santos UNIRIO - Universidade Federal do Estado do Rio de Janeiro, Alexander Serebrenik Eindhoven University of Technology | ||
10:30 30mPoster | Obfuscation-Resilient Software Plagiarism Detection with JPlag Posters Timur Sağlam Karlsruhe Institute of Technology (KIT), Sebastian Hahner Karlsruhe Institute of Technology (KIT), Larissa Schmid Karlsruhe Institute of Technology, Erik Burger Karlsruhe Institute of Technology (KIT) DOI Pre-print | ||
10:30 30mPoster | Micro-scale Concolic Testing Framework for Automated Test Data Generation Based on Path Coverage Posters Fangqing Liu , Han Huang South China University of Technology, Yi Xiang South China University of Technology | ||
10:30 30mPoster | What do you assume? A Theory of Security-Related Assumptions Posters Sophie Corallo Karlsruhe Institute of Technology (KIT), Thomas Weber , Lars König Karlsruhe Institute of Technology, Kathrin Leonie Schmidt Karlsruhe Institute of Technology, Frederik Reiche Karlsruhe Institute of Technology, Anne Koziolek Karlsruhe Institute of Technology | ||