论文提出因果跨层自愈框架,诊断 Edge-AI 异常来源
From Sensors to Silicon: Causal Cross-Layer Self-Healing Edge AI for Secure and Energy-Adaptive IoT Systems
这篇 arXiv 论文用因果推理引擎把传感器、推理、硬件、功耗的遥测数据打通,判断边缘设备异常的真正根因。做 IoT 或边缘部署的工程师值得看看它的诊断思路,和单层监控方案相比能区分恶意执行和硬件故障这类易混淆场景。
arXiv 论文《From Sensors to Silicon》提出一个面向 IoT 的因果跨层自愈 Edge-AI 框架。作者指出,现有边缘智能方案把传感器质量、推理行为、硬件可靠性、安全与能耗分层处理,导致难以判断性能退化到底来自传感器故障、数据分布偏移、恶意执行、硬件故障还是热应力。
该框架的核心机制是持续采集同步遥测数据,覆盖传感器健康度、推理不确定性、处理器硬件性能计数器、加速器与内存活动、功耗与热状态以及通信条件。一个时序感知的因果推理引擎据此估计异常行为的最可能起源,并量化诊断不确定性,支持多个扰动同时发生的情况。
论文定位于将 AI 从云端迁移到资源受限设备后的运维问题:同一物理节点上的感知、推理、微架构、可靠性与能耗被紧密耦合,分层诊断容易误判根因。对部署边缘推理的工程团队,这是把故障定位从人工排查转向自动化因果分析的思路参考。
From Sensors to Silicon: Causal Cross-Layer Self-Healing Edge AI for Secure and Energy-Adaptive IoT Systems
The migration of artificial intelligence from centralized cloud infrastructure to resource-constrained Internet-of-Things (IoT) devices reduces communication latency and improves data locality, but it also tightly couples sensing quality, inference behavior, microarchitectural activity, hardware reliability, security, and energy management within the same physical node. Existing edge-intelligence solutions predominantly address these dimensions in isolation, making it difficult to determine whether an observed degradation originates from sensor malfunction, data-distribution shift, malicious execution, hardware faults, or resource and thermal stress. This paper presents a causal cross-layer self-healing Edge-AI framework that continuously observes synchronized telemetry spanning sensor health, inference uncertainty, processor hardware-performance counters, accelerator and memory activity, power and thermal state, and communication conditions. A temporally informed causal reasoning engine estimates the most probable origin of abnormal behavior and quantifies diagnostic uncertainty, including under concurrent perturbations.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Edge AI, IoT, causal inference, edge computing.
Source attribution: curated from arXiv cs.AI (@Mostafa Darvishi).