STTR Phase I: Stochastic Computing Host Intrusion Detection System (HIDS) for IoT devices

这项小企业技术转移（STTR）第一阶段项目的更广泛影响将是通过使用一种新型的基于硬件的入侵检测系统，为物联网（IoT）设备提供新的额外安全保护层。对于大多数物联网设备来说，安全仍然是一个挑战，主要是由于这些设备的资源有限——有限的功率、计算能力和内存。提议的方法将通过检测此类设备中的异常行为来提供额外的物联网安全层，鼓励在许多新应用中采用。这个小型企业技术转移（STTR）第一阶段项目在物联网设备的基于硬件的主机入侵检测系统（HIDS）安全解决方案中使用随机计算（SC）。由于此类设备的资源限制性质，目前的物联网安全方法无法提供HIDS功能。因此，异常行为可能不会被发现。所提出的方法利用了SC的两个显著特性：(i)低功耗和硅面积要求，以及（ii）固有的概率性质，通过使用SC硬件和神经网络的组合来监控传入数据包的恶意活动，从而实现物联网设备的HIDS。该项目将为工业无人机开发、培训和测试基于sc的HIDS。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Technology Transfer (STTR) Phase I project will result from providing a new additional layer of security protection for Internet of Things (IoT) devices by using a novel hardware-based intrusion detection system. Security remains a challenge with most IoT devices, mainly due to the resource-constrained nature of these devices – limited power, computing power and memory. The proposed approach will provide an additional IoT security layer by enabling the detection of anomalous behavior in such devices, encouraging adoption in many new applications. This Small Business Technology Transfer (STTR) Phase I project employs Stochastic Computing (SC) in a hardware-based Host Intrusion Detection System (HIDS) security solution for IoT devices. Current approaches to IoT security are unable to provide HIDS capability due to the resource constrained nature of such devices. As a result, anomalous behavior may go undetected. The proposed approach exploits two salient properties of SC: (i) low power and silicon area requirements, and (ii) the inherently probabilistic nature, enabling a HIDS for IoT devices by using a combination of SC hardware and a Neural Network to monitor incoming packets for malicious activity. This project will develop, train and test an SC-based HIDS for industrial drones.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.