Scholarlink

<p>Data transmission at the nano-scale faces constraints that are notably different from those of conventional wireless systems, especially in terms of communication reliability, resource availability, and security. In the Internet of Nano-Things (IoNT) environments, protecting sensitive information while preserving acceptable network performance is still an open challenge, particularly when cryptographic mechanisms introduce additional processing and communication overhead. To address such an issue, this paper proposes an IoNT framework that integrates a DNA-based bio-molecular cryptographic scheme with a machine learning (ML) module aimed at dynamically predicting suitable security configurations under changing network conditions. The proposed approach is evaluated in a healthcare scenario based on a simulated artery environment, considering different routing/MAC combinations and varying numbers of nano-devices. Results show that the integration of ML enables improved robustness under congestion conditions, reducing packet loss by approximately 33–37% across the evaluated scenarios. Such an improvement comes at the cost of an additional latency overhead, ranging from about 18% in dense deployments to approximately 55% in smaller-scale scenarios. At the same time, the DNA-based scheme provides enhanced protection at the expense of a configuration-dependent delay increase, which becomes more evident as the number of nano-devices grows. Overall, the findings highlight the feasibility of combining adaptive ML-driven control with bio-inspired cryptography to balance security and performance in dynamic IoNT systems.</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

Learning at the nano-scale: how to dynamically protect data in nano-network transmissions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Alessandra Rizzardi,
  • Sabrina Sicari,
  • Luigi Alfredo Grieco,
  • Giuseppe Piro,
  • Jesus F. Cevallos-Moreno,
  • Alberto Coen-Porisini

摘要

Data transmission at the nano-scale faces constraints that are notably different from those of conventional wireless systems, especially in terms of communication reliability, resource availability, and security. In the Internet of Nano-Things (IoNT) environments, protecting sensitive information while preserving acceptable network performance is still an open challenge, particularly when cryptographic mechanisms introduce additional processing and communication overhead. To address such an issue, this paper proposes an IoNT framework that integrates a DNA-based bio-molecular cryptographic scheme with a machine learning (ML) module aimed at dynamically predicting suitable security configurations under changing network conditions. The proposed approach is evaluated in a healthcare scenario based on a simulated artery environment, considering different routing/MAC combinations and varying numbers of nano-devices. Results show that the integration of ML enables improved robustness under congestion conditions, reducing packet loss by approximately 33–37% across the evaluated scenarios. Such an improvement comes at the cost of an additional latency overhead, ranging from about 18% in dense deployments to approximately 55% in smaller-scale scenarios. At the same time, the DNA-based scheme provides enhanced protection at the expense of a configuration-dependent delay increase, which becomes more evident as the number of nano-devices grows. Overall, the findings highlight the feasibility of combining adaptive ML-driven control with bio-inspired cryptography to balance security and performance in dynamic IoNT systems.