Kumar Shashwat, Francis Hahn, Xinming Ou, Dmitry Goldgof, Jay Ligatti, Larrence Hall (University of South Florida), S. Raj Rajagoppalan (Resideo), Armin Ziaie Tabari (CipherArmor)

Large language models (LLM) are perceived to offer promising  potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the use of LLMs in software pentesting, where the main task is to automatically identify software security vulnerabilities in source code. We hypothesize that an LLM-based AI agent can be improved over time for a specific security task as human operators interact with it. Such improvement can be made, as a first step, by engineering prompts fed to the LLM based on the responses produced, to include relevant contexts and structures so that the model provides more accurate results. Such engineering efforts become sustainable if the prompts that are engineered to produce better results on current tasks, also produce better results on future unknown tasks. To examine this hypothesis, we utilize the OWASP Benchmark Project 1.2 which contains 2,740 hand-crafted source code test cases containing various types of vulnerabilities. We divide the test cases into training and testing data, where we engineer the prompts based on the training data (only), and evaluate the final system on the testing data. We compare the AI agent’s performance on the testing data against the performance of the agent without the prompt engineering. We also compare the AI agent’s results against those from SonarQube, a widely used static code analyzer for security testing. We built and tested multiple versions of the AI agent using different off-the-shelf LLMs – Google’s Gemini-pro, as well as OpenAI’s GPT-3.5-Turbo and GPT-4-Turbo (with both chat completion and assistant APIs). The results show that using LLMs is a viable approach to build an AI agent for software pentesting that can improve through repeated use and prompt engineering.

View More Papers

A Cross-Verification Approach with Publicly Available Map for Detecting...

Takami Sato, Ningfei Wang (University of California, Irvine), Yueqiang Cheng (NIO Security Research), Qi Alfred Chen (University of California, Irvine)

Read More

Understanding the Implementation and Security Implications of Protective DNS...

Mingxuan Liu (Zhongguancun Laboratory; Tsinghua University), Yiming Zhang (Tsinghua University), Xiang Li (Tsinghua University), Chaoyi Lu (Tsinghua University), Baojun Liu (Tsinghua University), Haixin Duan (Tsinghua University; Zhongguancun Laboratory), Xiaofeng Zheng (Institute for Network Sciences and Cyberspace, Tsinghua University; QiAnXin Technology Research Institute & Legendsec Information Technology (Beijing) Inc.)

Read More

SyzBridge: Bridging the Gap in Exploitability Assessment of Linux...

Xiaochen Zou (UC Riverside), Yu Hao (UC Riverside), Zheng Zhang (UC RIverside), Juefei Pu (UC RIverside), Weiteng Chen (Microsoft Research, Redmond), Zhiyun Qian (UC Riverside)

Read More

Cyclops: Binding a Vehicle’s Digital Identity to its Physical...

Lewis William Koplon, Ameer Ghasem Nessaee, Alex Choi (University of Arizona, Tucson), Andres Mentoza (New Mexico State University, Las Cruces), Michael Villasana, Loukas Lazos, Ming Li (University of Arizona, Tucson)

Read More