Defense: Towards Low-cost and Scalable Network Services: from Algorithms to Systems

Minmei Wang
Computer Engineering PhD Candidate
Location
Virtual Event
Advisor
Chen Qian

Join us on Zoom: https://ucsc.zoom.us/j/5702123928?pwd=TVlLMzEwWFIwc2VORHJLdVJiek5TUT09 / Passcode: 066521

Description: With emerging technology such as Wi-Fi, 4G, and 5G, more heterogeneous mobile devices, including low-power IoT devices, are connected to the Internet to request services. Those billions of connected devices generate a large volume of data, making us rethink providing low-cost and scalable network services to improve users' experience. We summarized various network devices according to different layers, including the perception, network, support, and application layers. My thesis research focuses on the perception layer and the network support layer. Specifically, the thesis focuses on two types of widely-used network services.

The first type of service is security and privacy service for end devices. Mainly, I focus on two fundamental problems. 1) speeding up the certificate validation process, which is the basic and important step before a secure channel is built between end devices. 2) privacy protection when end devices communicate with remote cloud servers. One finding is that compact and efficient data structures and algorithms are essential in designing various network services. Thus, I utilized an efficient data structure called Othello to develop the Collaborative Certificate Validation protocol (CCV), which provides a fast certificate validation for IoT devices. In addition, I designed Vacuum Filters, an efficient data structure to support approximate membership queries. Vacuum Filters can be applied for many applications, such as IoT security, data management, and network functions. Based on Vacuum filters, I designed the LOIS framework to protect users' privacy when end devices communicate with remote cloud servers.

The second type of service is the design of efficient network functions (NFs). NFs are fundamental services on the network support layer. They also rely on efficient data structures and algorithms to achieve memory and computation efficiency. We observed that multiple, co-existed NFs on the same device have become common in today's programmable networks. Thus, I designed a tool called HyperMerger which can automatically generate resource-efficient consolidated algorithms to support co-existed NFs simultaneously for both hardware and software platforms.