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

Beyond Conventional Triggers: Auto-Contextualized Covert Triggers for Android Logic...

Ye Wang (Department of Electrical Engineering and Computer Science, Institute for Information Sciences, The University of Kansas), Bo Luo (Department of Electrical Engineering and Computer Science, Institute for Information Sciences, The University of Kansas), Fengjun Li (Department of Electrical Engineering and Computer Science, Institute for Information Sciences, The University of Kansas)

Read More

Context Relay for Long-Running Penetration-Testing Agents

Marius Vangeli (KTH Royal Institute of Technology, Sweden), Joel Brynielsson (KTH Royal Institute of Technology, Sweden and FOI Swedish Defence Research Agency, Sweden), Mika Cohen (KTH Royal Institute of Technology, Sweden and FOI Swedish Defence Research Agency, Sweden), Farzad Kamrani (FOI Swedish Defence Research Agency, Sweden)

Read More

Decompiling the Synergy: An Empirical Study of Human–LLM Teaming...

Zion Leonahenahe Basque (Arizona State University), Samuele Doria (University of Padua), Ananta Soneji (Arizona State University), Wil Gibbs (Arizona State University), Adam Doupe (Arizona State University), Yan Shoshitaishvili (Arizona State University), Eleonora Losiouk (University of Padua), Ruoyu “Fish” Wang (Arizona State University), Simone Aonzo (EURECOM)

Read More