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

Usability Issues in Differential Privacy Libraries: A Study from...

Ravi Mahankali (University of Bristol), Jo Hallett (University of Bristol)

Read More

Non-Disruptive Disruption: An Empirical Experience of Introducing LLMs in...

Francis Hahn (University of South Florida), Mohd Mamoon (University of Kansas), Alexandru G. Bardas (University of Kansas), Michael Collins (University of Southern California – ISI), Jaclyn Lauren Dudek (University of Kansas), Daniel Lende (University of South Florida), Xinming Ou (University of South Florida), S. Raj Rajagopalan (Resideo Technologies)

Read More

Hey there! You are using WhatsApp: Enumerating Three Billion...

Gabriel K. Gegenhuber (University of Vienna, Faculty of Computer Science and UniVie Doctoral School Computer Science), Philipp E. Frenzel (SBA Research), Maximilian Günther (University of Vienna, Faculty of Computer Science), Johanna Ullrich (University of Vienna, Faculty of Computer Science), Aljosha Judmayer (University of Vienna, Faculty of Computer Science)

Read More