Internet of Medical Things (IoMT) is now worth a billion dollar market. While offering enormous benefit, the prevalent and open environment of IoMT ecosystem can be a potential target of varied evolving cyber threats and attacks. Further, extensive connectivity of IoMT devices and their dynamic massive heterogeneous communication can create a new attack surface for sophisticated multivector malware attacks. There is a dire need to protect the forthcoming IoMT industrial revolution from varied evolving cyber threats and attacks. The authors propose a hybrid DL-driven SDN-enabled IoMT framework leveraging Convolutional Neural Network (CNN) and Cuda Deep Neural Network Long Short Term Memory (cuDNNLSTM) for a timely and efficient detection of sophisticated multivector malware botnets. For comprehensive evaluation, a state-of-the-art IoMT dataset and standard performance metrics have been employed. For verification purpose, we compare our proposed framework with our constructed hybrid DL-driven architectures and benchmark algorithms. Our proposed technique outperforms in terms of detection accuracy and testing efficiency. Finally, we also perform 10-fold cross validation to utterly show unbiased results.

医疗物联网（IoMT）现在价值十亿美元。尽管IoMT生态系统具有广泛的优势，但其普遍开放的环境可能成为各种不断发展的网络威胁和攻击的潜在目标。此外，IoMT设备的广泛连接及其动态的大规模异构通信可以为复杂的多向量恶意软件攻击创建新的攻击面。迫切需要保护即将来临的IoMT工业革命免受各种不断发展的网络威胁和攻击。作者提出了一种混合的，由DL驱动的，基于SDN的IoMT框架，该框架利用卷积神经网络（CNN）和Cuda深层神经网络长期短期记忆（cuDNNLSTM）来及时有效地检测复杂的多矢量恶意软件僵尸网络。为了进行综合评估，我们采用了最新的IoMT数据集和标准性能指标。为了进行验证，我们将建议的框架与构建的混合DL驱动的体系结构和基准算法进行了比较。我们提出的技术在检测准确度和测试效率方面均胜过。最后，我们还执行10倍交叉验证，以完全显示出公正的结果。