可信智能体人工智能：威胁态势、防御架构与开放挑战的综合网络安全与系统综述

中文摘要 AI 辅助

从被动基础模型向自主、目标导向的智能体人工智能系统的转变，通过耦合递归认知推理循环、持久记忆架构、实时工具执行平面和多智能体协作拓扑，引入了前所未有的能力。然而，赋予概率神经核心跨文件系统、网络和云基础设施的执行权限，瓦解了经典的安全边界：自然语言同时充当输入数据、内部控制代码和通信协议，暴露了一个图灵完备的爆炸半径，其中不可信数据代表可执行指令。本综述为可信智能体人工智能提供了一个全面的系统安全参考框架，综合了206项基础研究和监管标准。我们将通用智能体架构形式化为一个有状态的五元组，并建立一个六维可信度分类法，涵盖安全性、安全、隐私、可解释性、公平性和问责制。我们系统地分析了执行循环内部和交互平面上的威胁面，构建了一个多层零信任纵深防御架构，集成了双大语言模型隔离、基于能力的访问控制、内核eBPF探针和沙箱运行时，审查了标准化评估基准，并将技术控制映射到国际人工智能治理框架。

英文摘要

The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling recursive cognitive reasoning loops, persistent memory architectures, live tool execution planes, and multi-agent collaboration topologies. However, granting probabilistic neural cores execution authority across filesystems, networks, and cloud infrastructure dissolves classical security perimeters: natural language simultaneously serves as input data, internal control code, and communication protocols, exposing a Turing-complete blast radius where untrusted data represents executable instructions. This survey delivers a comprehensive systems-security reference framework for trustworthy agentic AI, synthesizing 206 foundational studies and regulatory standards. We formalize the general agent architecture as a stateful 5-tuple and establish a 6-dimensional trustworthiness taxonomy covering security, safety, privacy, explainability, fairness, and accountability. We systematically analyze threat surfaces across intra-execution loops and interaction planes, formulate a multi-layered zero-trust defense-in-depth architecture integrating Dual-LLM isolation, Capability-Based Access Control, kernel eBPF probes, and sandboxed runtimes, review standardized evaluation benchmarks, and map technical controls to international AI governance frameworks.

发表机构

• Yazd University（亚兹德大学）

机构由 AI 辅助整理，请以论文原文为准。