no code implementations • 28 Feb 2024 • Fangzhou Wu, Ning Zhang, Somesh Jha, Patrick McDaniel, Chaowei Xiao
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on.
no code implementations • 26 Feb 2024 • Fangzhou Wu, Shutong Wu, Yulong Cao, Chaowei Xiao
To evaluate the effectiveness of the proposed methodology, we conducted extensive experiments using 7 plugin-based ChatGPT Web Agents, 8 Web GPTs, and 3 different open-source Web Agents.
no code implementations • 8 Dec 2023 • Fangzhou Wu, Qingzhao Zhang, Ati Priya Bajaj, Tiffany Bao, Ning Zhang, Ruoyu "Fish" Wang, Chaowei Xiao
Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times.
no code implementations • 7 Dec 2023 • Fangzhou Wu, Xiaogeng Liu, Chaowei Xiao
In this paper, we introduce DeceptPrompt, a novel algorithm that can generate adversarial natural language instructions that drive the Code LLMs to generate functionality correct code with vulnerabilities.
no code implementations • 8 Mar 2022 • Xiaogeng Liu, Haoyu Wang, Yechao Zhang, Fangzhou Wu, Shengshan Hu
The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models.