Scholarlink

<p>Healthcare fog computing enables low-latency processing of sensitive medical data by distributing computation closer to data sources such as medical IoT devices and edge systems. Despite these advantages, the decentralized and heterogeneous nature of fog environments introduces substantial challenges related to security, privacy, and performance, particularly under sophisticated cyber threats, data tampering risks, and emerging quantum computing attacks. To address these challenges, this paper proposes Q-ZeroFog, a post-quantum security framework designed to enhance privacy, resilience, and performance in healthcare fog computing environments. Q-ZeroFog integrates a quantum-resistant blockchain layer, an AI-driven software-defined networking (SDN) control plane, and an adaptive zero-trust security model to ensure secure and efficient operation of healthcare fog networks and e-health applications. The framework employs post-quantum cryptographic schemes to protect sensitive healthcare data against quantum-enabled attacks, reinforcement learning–based SDN control for dynamic traffic optimization, and digital twin technology for proactive fault detection and autonomous recovery of fog nodes. In addition, homomorphic encryption is applied to lightweight healthcare data analytics (e.g., aggregation and threshold-based computations), enabling privacy-preserving processing without exposing raw patient data. Extensive simulations conducted in a controlled, permissioned healthcare fog environment demonstrate that Q-ZeroFog consistently outperforms existing security models across multiple performance metrics. The framework achieves intrusion detection rates of 99.15%, 98.45%, and 98.00% under low, medium, and high network loads, respectively, surpassing benchmark models such as ZT-1 and FogGuard. Data integrity reaches up to 99.20%, while task completion rates exceed 97.85% across all load conditions. Furthermore, Q-ZeroFog delivers reduced latency (130–210 ms), lower energy consumption (95.5 Wh for fog nodes and 21.75 Wh for IoT devices), improved scalability, and minimal privacy leakage (as low as 1.25% under high load). These results validate Q-ZeroFog as a scalable, privacy-preserving, and high-performance post-quantum security framework capable of meeting the stringent requirements of latency-sensitive healthcare fog computing applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A unified post-quantum zero-trust architecture with AI-driven orchestration for secure healthcare fog networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月1日

查看全文
  • Umesh Kumar Lilhore,
  • Santosh Kumar,
  • Roobaea Alroobaea,
  • Majed Alsafyani,
  • Abdullah M. Baqasah,
  • Sultan Algarni,
  • Lidia Gosy Tekeste

摘要

Healthcare fog computing enables low-latency processing of sensitive medical data by distributing computation closer to data sources such as medical IoT devices and edge systems. Despite these advantages, the decentralized and heterogeneous nature of fog environments introduces substantial challenges related to security, privacy, and performance, particularly under sophisticated cyber threats, data tampering risks, and emerging quantum computing attacks. To address these challenges, this paper proposes Q-ZeroFog, a post-quantum security framework designed to enhance privacy, resilience, and performance in healthcare fog computing environments. Q-ZeroFog integrates a quantum-resistant blockchain layer, an AI-driven software-defined networking (SDN) control plane, and an adaptive zero-trust security model to ensure secure and efficient operation of healthcare fog networks and e-health applications. The framework employs post-quantum cryptographic schemes to protect sensitive healthcare data against quantum-enabled attacks, reinforcement learning–based SDN control for dynamic traffic optimization, and digital twin technology for proactive fault detection and autonomous recovery of fog nodes. In addition, homomorphic encryption is applied to lightweight healthcare data analytics (e.g., aggregation and threshold-based computations), enabling privacy-preserving processing without exposing raw patient data. Extensive simulations conducted in a controlled, permissioned healthcare fog environment demonstrate that Q-ZeroFog consistently outperforms existing security models across multiple performance metrics. The framework achieves intrusion detection rates of 99.15%, 98.45%, and 98.00% under low, medium, and high network loads, respectively, surpassing benchmark models such as ZT-1 and FogGuard. Data integrity reaches up to 99.20%, while task completion rates exceed 97.85% across all load conditions. Furthermore, Q-ZeroFog delivers reduced latency (130–210 ms), lower energy consumption (95.5 Wh for fog nodes and 21.75 Wh for IoT devices), improved scalability, and minimal privacy leakage (as low as 1.25% under high load). These results validate Q-ZeroFog as a scalable, privacy-preserving, and high-performance post-quantum security framework capable of meeting the stringent requirements of latency-sensitive healthcare fog computing applications.