Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study
School of Informatics, Computing, and Cyber Systems（信息学、计算与网络系统学院）；Northern Arizona University（北亚利桑那大学）；Department of Software Science（软件科学系）；Tallinn University of Technology（塔林技术大学）
Neha Nagaraja, Hayretdin Bahsi
备注：
To appear in the HealthSec Workshop at the 2025 IEEE Annual Computer Security Applications Conference (ACSAC)
While incorporating LLMs into systems offers significant benefits in critical application areas such as healthcare, new security challenges emerge due to the potential cyber kill chain cycles that combine adversarial model, prompt injection and conventional cyber attacks. Threat modeling methods enable the system designers to identify potential cyber threats and the relevant mitigations during the early stages of development. Although the cyber security community has extensive experience in applying these methods to software-based systems, the elicited threats are usually abstract and vague, limiting their effectiveness for conducting proper likelihood and impact assessments for risk prioritization, especially in complex systems with novel attacks surfaces, such as those involving LLMs. In this study, we propose a structured, goal driven risk assessment approach that contextualizes the threats with detailed attack vectors, preconditions, and attack paths through the use of attack trees. We demonstrate the proposed approach on a case study with an LLM agent-based healthcare system. This study harmonizes the state-of-the-art attacks to LLMs with conventional ones and presents possible attack paths applicable to similar systems. By providing a structured risk assessment, this study makes a significant contribution to the literature and advances the secure-by-design practices in LLM-based systems.
LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data
Department of Information Systems and Cybersecurity, The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校信息系统与网络安全系）；School of Engineering Medicine, Texas A&M University（德克萨斯农工大学工程医学院）；Department of Family and Community Medicine, The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校家庭与社区医学系）
Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models
Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；Mount Sinai Hospital（西奈山医院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Pittsburgh School of Medicine（匹兹堡大学医学院）
Dr. Bias: Social Disparities in AI-Powered Medical Guidance
Mila - Quebec AI Institute（魁北克人工智能研究所）；Centre for Advanced Studies in Bioscience Innovation Law, Faculty of Law, University of Copenhagen（哥本哈根大学法学院生物科学创新研究中心）；Center for the Study of Democratic Citizenship, Department of Political Science, McGill University（麦吉尔大学政治科学系民主公民研究所以及）
Blockchain Powered Edge Intelligence for U-Healthcare in Privacy Critical and Time Sensitive Environment
Shanghai Key Laboratory of Intelligent Information Processing Lab, Fudan University, China（上海智能信息处理实验室，复旦大学，中国）；Turku Intelligent Embedded and Robotic Systems (TIERS) Lab, Faculty of Technology, University of Turku, Finland（图尔库智能嵌入式与机器人系统（TIERS）实验室，技术学院，图尔库大学，芬兰）；Department of Engineering and Architecture, University of Parma, Italy（工程与建筑系，帕尔马大学，意大利）；TIERS Lab, University of Turku, Finland（TIERS实验室，图尔库大学，芬兰）；School of Information Science and Technology, Fudan University, Shanghai, China（信息科学与技术学院，复旦大学，上海，中国）；Robotics and Autonomous Systems at the University of Turku（图尔库大学的机器人与自主系统）
PriEval-Protect: A Unified Framework for Privacy Evaluation and Protection in Healthcare Systems
National Institute of Applied Science and Technology INSAT（国立应用科学与技术学院）；Efrei Research Lab, Efrei, Paris-Panthéon-Assas University（巴黎-潘特翁-阿萨斯大学埃弗雷伊研究实验室）；LARIA Research Lab, National School Of Computer Science ENSI（国立计算机科学学院拉里亚研究实验室）
Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
University of Notre Dame（圣约翰大学）；Northeastern University（东北大学）；Virginia Tech（弗吉尼亚理工大学）；University of Washington（华盛顿大学）；Johns Hopkins University（约翰霍普金斯大学）
An Agentic Multi-Agent Architecture for Cybersecurity Risk Management
Lead Software Engineer, BigCommerce（BigCommerce 首席软件工程师）；University at Buffalo, The State University of New York, Buffalo, NY, USA（纽约州立大学布法罗分校）；Software Engineer, Microsoft（微软软件工程师）；Senior Software Engineer, Amazon（亚马逊高级软件工程师）
