Yuqiao Yang (UESTC), Yongzhao Zhang (UESTC), Wenhao Liu (GoGoByte Technology), Jun Li (GoGoByte Technology), Pengtao Shi (GoGoByte Technology), DingYu Zhong (UESTC), Jie Yang (UESTC), Ting Chen (UESTC), Sheng Cao (UESTC), Yuntao Ren (UESTC), Yongyue Wu (UESTC), Xiaosong Zhang (UESTC)

As modern vehicles evolve into intelligent and connected systems, their growing complexity introduces significant cybersecurity risks. Threat Analysis and Risk Assessment (TARA) has therefore become essential for managing these risks under mandatory regulations. However, existing TARA automation methods rely on static threat libraries, limiting their utility in the detailed, function-level analyses demanded by industry. This paper introduces DefenseWeaver, the first system that automates function-level TARA using component-specific details and large language models (LLMs). DefenseWeaver dynamically generates attack trees and risk evaluations from system configurations described in an extended OpenXSAM++ format, then employs a multi-agent framework to coordinate specialized LLM roles for more robust analysis. To further adapt to evolving threats and diverse standards, DefenseWeaver incorporates Low-Rank Adaptation (LoRA) fine-tuning and Retrieval-Augmented Generation (RAG) with expert-curated TARA reports. We validated DefenseWeaver through deployment in four automotive security projects, where it identified 11 critical attack paths, verified through penetration testing, and subsequently reported and remediated by the relevant automakers and suppliers. Additionally, DefenseWeaver demonstrated cross-domain adaptability, successfully applying to unmanned aerial vehicles (UAVs) and marine navigation systems. In comparison to human experts, DefenseWeaver outperformed manual attack tree generation across six assessment scenarios. Integrated into commercial cybersecurity platforms such as UAES and Xiaomi, DefenseWeaver has generated over 8,200 attack trees. These results highlight its ability to significantly reduce processing time, and its scalability and transformative impact on cybersecurity across industries.

View More Papers

Better Safe than Sorry: Uncovering the Insecure Resource Management...

Yizhe Shi (Fudan University), Zhemin Yang (Fudan University), Dingyi Liu (Fudan University), Kangwei Zhong (Fudan University), Jiarun Dai (Fudan University), Min Yang (Fudan University)

Read More

One Small Patch for a File, One Giant Leap...

Julian Rederlechner (CISPA Helmholtz Center for Information Security), Ulysse Planta (CISPA Helmholtz Center for Information Security), Ali Abbasi (CISPA Helmholtz Center for Information Security)

Read More

Achieving Zen: Combining Mathematical and Programmatic Deep Learning Model...

David Oygenblik (Georgia Institute of Technology), Dinko Dermendzhiev (Georgia Institute of Technology), Filippos Sofias (Georgia Institute of Technology), Mingxuan Yao (Georgia Institute of Technology), Haichuan Xu (Georgia Institute of Technology), Runze Zhang (Georgia Institute of Technology), Jeman Park (Kyung Hee University), Amit Kumar Sikder (Iowa State University), Brendan Saltaformaggio (Georgia Institute of Technology)

Read More