Benefiting from the massive available data provided by Internet of multimedia things (IoMT), enormous intelligent services requiring information of various types to make decisions are emerging. Generally, the IoMT devices are equipped with limited computing power, interfering with the process of computation-intensive services. Currently, to satisfy a wide range of service requirements, the novel computing paradigms, i.e., cloud computing and edge computing, can potentially be integrated for service accommodation. Nevertheless, the private information (i.e., location, service type, etc.) in the services is prone to spilling out during service offloading in the cloud-edge computing. To avoid privacy leakage while improving service utility, including the service response time and energy consumption for service executions, a <underline>L</underline>ocality-sensitive-hash (LSH)-based <underline>o</underline>ffloading <underline>m</underline>ethod, named LOM, is devised. Specifically, LSH is leveraged to encrypt the feature information for the services offloaded to the edge servers with the intention of privacy preservation. Eventually, comparative experiments are conducted to verify the effectiveness of LOM with respect to promoting service utility.

中文翻译：

---

云边一体化环境下基于LSH的物联网业务卸载方法

受益于多媒体物联网（IoMT）提供的海量可用数据，需要各类信息进行决策的海量智能服务正在兴起。通常，物联网设备的计算能力有限，干扰了计算密集型服务的进程。目前，为了满足广泛的服务需求，新的计算范式，即云计算和边缘计算，可以潜在地集成用于服务住宿。然而，在云边缘计算的服务卸载过程中，服务中的私有信息（即位置、服务类型等）容易溢出。为了在提高服务效用（包括服务响应时间和服务执行的能耗）的同时避免隐私泄露，<underline>L< 设计了基于 /underline>ocality-sensitive-hash (LSH) 的 <underline>o</underline>ff 加载 <underline>m</underline> 方法，命名为 LOM。具体来说，LSH 用于加密卸载到边缘服务器的服务的特征信息，以保护隐私。最后，通过对比实验验证了 LOM 在提升服务效用方面的有效性。