Structured access is an emerging paradigm for the safe deployment of artificial intelligence (AI). Instead of openly disseminating AI systems, developers facilitate controlled, arm's length interactions with their AI systems. The aim is to prevent dangerous AI capabilities from being widely accessible, whilst preserving access to AI capabilities that can be used safely. The developer must both restrict how the AI system can be used, and prevent the user from circumventing these restrictions through modification or reverse engineering of the AI system. Structured access is most effective when implemented through cloud-based AI services, rather than disseminating AI software that runs locally on users' hardware. Cloud-based interfaces provide the AI developer greater scope for controlling how the AI system is used, and for protecting against unauthorized modifications to the system's design. This chapter expands the discussion of "publication norms" in the AI community, which to date has focused on the question of how the informational content of AI research projects should be disseminated (e.g., code and models). Although this is an important question, there are limits to what can be achieved through the control of information flows. Structured access views AI software not only as information that can be shared but also as a tool with which users can have arm's length interactions. There are early examples of structured access being practiced by AI developers, but there is much room for further development, both in the functionality of cloud-based interfaces and in the wider institutional framework.
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
CSX-AI；University of Liverpool（利物浦大学）；Carl von Ossietzky Universität Oldenburg（奥尔登堡卡尔·冯·奥西特齐克大学）；Austrian Institute of Technology（奥地利技术研究院）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）
Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories
Shanghai Innovation Institute（上海创新研究院）；Nankai University（南开大学）；East China Normal University（华东师范大学）；AI for Science Institute, Beijing（北京人工智能科学研究院）；Peking University（北京大学）；DP Technology（DP技术公司）；Shanghai Jiao Tong University（上海交通大学）；National Key Laboratory of Advanced Micro and Nano Manufacture Technology, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai 200240, China（上海交通大学国家先进微纳米制造技术重点实验室，集成电路学院，上海200240，中国）
Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
Department of Chemical Engineering, Imperial College London（帝国理工学院化学工程系）；Shell Information Technology International BV（壳牌信息科技国际有限公司）；Shell Global Solutions International BV（壳牌全球解决方案国际有限公司）
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
Department of Statistics, University of Georgia（统计学系，佐治亚大学）；School of Computing, University of Georgia（计算学院，佐治亚大学）；Department of Biostatistics, Boston University（生物统计学系，波士顿大学）；Department of Epidemiology & Biostatistics, University of Georgia（流行病学与生物统计学系，佐治亚大学）；School of Computer and Cyber Sciences, Augusta University（计算机与网络科学学院，奥古斯塔大学）；School of Electrical and Computer Engineering, University of Georgia（电气与计算机工程学院，佐治亚大学）；Department of Statistics & Data Science, University of Arizona（统计学与数据科学系，亚利桑那大学）；Kellogg School of Management, Northwestern University（凯洛格管理学院，西北大学）；Department of Statistics, Harvard University（统计学系，哈佛大学）；School of Computer Science, Carnegie Mellon University（计算机科学学院，卡内基梅隆大学）
