Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Models
DevOps is a necessity in many industries, including the development of Autonomous Vehicles. Consequently, there would be a need for iterative loops of activities in each cycle of SafetyOps, that would reduce the speed of each cycle. One of these activities is “Hazard Analysis & Risk Assessment” (HARA), which is an essential step to start the safety requirements specification. As a potential approach to increase the speed of this step in SafetyOps, we have delved into the capabilities of Large Language Models (LLMs), a fast-expanding technology that is significantly influencing a variety of domains. Although the engineering domain has already experienced the impact of LLMs in tasks such as code generation and requirements specification, our objective is to systematically assess their potential for application in the field of safety engineering. In this paper, we propose a framework for supporting a higher degree of automation of HARA with LLMs and demonstrate its use in an industry workflow. The efficacy of this approach has been evaluated through quality assurance reviews (i.e., Verification and Confirmation Review) with safety experts in the field and Joint follow-up meetings. Despite our endeavors to automate as much of the process as possible, the expert review remains necessary to ensure the validity and correctness of the analysis results, with necessary modifications made accordingly.
Mon 15 AprDisplayed time zone: Lisbon change
14:00 - 15:30 | |||
14:00 15mTalk | A Combinatorial Testing Approach to Hyperparameter OptimizationDistinguished paper Award Candidate Research and Experience Papers Krishna Khadka The University of Texas at Arlington, Jaganmohan Chandrasekaran Virginia Tech, Jeff Yu Lei University of Texas at Arlington, Raghu Kacker National Institute of Standards and Technology, D. Richard Kuhn National Institute of Standards and Technology | ||
14:15 15mTalk | Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs Research and Experience Papers | ||
14:30 10mTalk | LLMs for Test Input Generation for Semantic Applications Research and Experience Papers Zafaryab Rasool Applied Artificial Intelligence Institute, Deakin University, Scott Barnett Applied Artificial Intelligence Institute, Deakin University, David Willie Applied Artificial Intelligence Institute, Deakin University, Stefanus Kurniawan Deakin University, Sherwin Balugo Applied Artificial Intelligence Institute, Deakin University, Srikanth Thudumu Deakin University, Mohamed Abdelrazek Deakin University, Australia | ||
14:40 10mTalk | (Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIs Research and Experience Papers MA Wanqin The Hong Kong University of Science and Technology, Chenyang Yang Carnegie Mellon University, Christian Kästner Carnegie Mellon University | ||
14:50 10mTalk | Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Models Research and Experience Papers Ali Nouri Volvo cars & Chalmers University of Technology, Beatriz Cabrero-Daniel University of Gothenburg, Fredrik Torner Volvo cars, Hakan Sivencrona Zenseact AB, Christian Berger Chalmers University of Technology, Sweden | ||
15:00 10mTalk | ML-On-Rails: Safeguarding Machine Learning Models in Software Systems – A Case Study Research and Experience Papers Hala Abdelkader Applied Artificial Intelligence Institute, Deakin University, Mohamed Abdelrazek Deakin University, Australia, Scott Barnett Applied Artificial Intelligence Institute, Deakin University, Jean-Guy Schneider Monash University, Priya Rani RMIT University, Rajesh Vasa Deakin University, Australia | ||
15:10 20mLive Q&A | Test - Q&A Session Research and Experience Papers | ||