Date of Award

5-29-2024

Document Type

Thesis

Publisher

Santa Clara : Santa Clara University, 2024

Department

Computer Science and Engineering

First Advisor

Sean Choi

Abstract

Ransomware, a form of malware that restricts access to data until a ransom is paid, accounts for 20% of all cyber crimes. Although companies and organizations often require their personnel to take training for awareness of such bad actors, social engineering is constantly evolving and ransomware slips through the cracks every year. In this paper, we suggest a system that would help detect ransomware using a Smart Network Interface Card (SmartNIC) which runs machine learning algorithms to detect ransomware before it enters the system. This relieves computers in the network of the burden of detecting malware, freeing CPU capacity to do other work. Using previous network data captured while running ransomware binaries, we trained models that accurately predict whether network traffic contains ransomware using only packet payloads. Our results suggest that payload analysis could be a valid in-network solution to malware detection.

Download

Share

COinS