AI部署问责工程：安全关键社会技术系统中可问责AI的愿景
AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical Systems
浏览论文内容
中文总结 AI 辅助
本文提出AI部署问责工程（ADAE），将问责视为部署层属性，通过四个支柱研究议程，确保安全关键系统中已部署AI系统持续在可接受风险内运行并支持及时干预。
中文摘要 AI 辅助
人工智能系统正迅速成为医疗保健、金融、公共服务及其他安全关键领域的关键组成部分。然而，用于评估这些系统的工程实践仍以模型为中心，主要强调部署前的准确性、鲁棒性、公平性和可解释性等属性。当AI系统在由分布偏移、制度约束、人类反馈循环、隐私要求以及多个AI智能体之间交互所刻画的不断变化的社会技术环境中运行时，这些属性是必要的但不够充分。这篇愿景论文引入了AI部署问责工程（ADAE），一个提议的AI工程子学科，关注为已部署的AI系统建立可衡量、持续且可操作的问责制。ADAE将问责视为部署层属性，而非仅仅是单个模型的属性。它旨在确定启用AI的系统是否继续在可接受的风险限度内运行，识别失败出现的上下文，将失败归因于交互的技术和人类组件，将技术失败转化为下游后果，并支持及时干预。我们阐述了一个围绕四个相互关联支柱构建的研究议程：上下文相关失败模式的结构化发现、隐私保护的问责测量、代理AI的系统级风险分析，以及将技术失败转化为运营和制度风险。更广泛的目标是为安全关键应用中的可问责AI部署建立基础原则、数学工具和系统架构。
英文摘要
Artificial intelligence systems are rapidly becoming critical components in healthcare, finance, public services, and other safety-critical domains. Yet the engineering practices used to evaluate these systems remain predominantly model-centric, emphasizing properties such as accuracy, robustness, fairness, and interpretability before deployment. These properties are necessary but insufficient once an AI system operates within an ever changing socio-technical environment characterized by distribution shifts, institutional constraints, human feedback loops, privacy requirements, and interactions among multiple AI agents. This vision paper introduces AI Deployment Accountability Engineering (ADAE), a proposed AI engineering subdiscipline concerned with establishing measurable, continuous, and actionable accountability for deployed AI systems. ADAE treats accountability as a deployment-layer property rather than solely as a property of an individual model. It seeks to determine whether an AI-enabled system continues to operate within acceptable risk limits, identify the contexts in which failures emerge, attribute failures across interacting technical and human components, translate technical failures into downstream consequences, and support timely intervention. We articulate a research agenda built around four interconnected pillars: structured discovery of context-dependent failure modes, privacy-preserving accountability measurement, system-level risk analysis for agentic AI, and translation of technical failures into operational, and institutional risks. The broader goal is to establish foundational principles, mathematical tools, and system architectures for accountable AI deployment across safety-critical applications.
发表机构
- Virginia Tech（弗吉尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。
