Professor Arpit Gupta receives grant from Verizon Innovations

September 7, 2020

Professor Arpit Gupta receives grant from Verizon Innovations to scale Network Security

By Natalia Diaz Amabilis, PR Assistant

Verizon has announced its partnership with the University of California, Santa Barbara, which aims to test the use of AI and machine learning to develop improved security around the flow of information and how it is interpreted and used.

In recent years, we have witnessed two trends: an exponential increase in the number of Internet-connected devices and applications, and an increase in the sophistication of cyber attacks over the Internet. Detecting such complex security events requires an in-depth analysis of network traffic in real-time. Though, we have network-security systems capable of such complex network traffic analysis (e.g., Suricata, Zeek, etc.), scaling such devices is challenging. Lowering the guard against cyber attacks is not an option for mobile service providers. As a result, they are forced to invest heavily in upgrading their security infrastructure. However, such an approach is not sustainable in the longer run, especially as we expect an increase in traffic volume with the rollout of next-generation mobile networks (e.g., 5G)

With this grant, the team at UCSB will explore how to scale network security solutions. In this project, Dr. Gupta's team will develop new data structures and algorithms that use programmable data-plane to scale network security systems, such as intrusion detection systems (IDS) and firewalls. The award is highly competitive and recognizes the quality of research and its importance to the industry.

Dr. Gupta joined the computer science department at UCSB in Fall 2019 and co-directs the Systems and Networking Lab (SNL). He is also affiliated with UCSB's Center for Responsible Machine Learning (CRML). His research focuses on making distributed network-telemetry systems scalable and robust to traffic dynamics and building self-driving network-management systems for the last-mile networks.