top of page


Anomaly Detection

anomaly detection.png

Traditional anomaly detection approaches tend to generate a large number of false alerts due to lack of proper features and inherent weakness of anomaly detection algorithms. Features are usually selected or created for characterizing behaviors of networks, users or systems. In this project, we address this limitation and aim to develop a multi agents based anomaly detection system, including a large number of different detection agents and various features from different sources. The main goal of this project is to obtain the minimum number of false alerts through the system’s self-learning-fixing capability.

Internet Traffic Classification

application discovery.png

Classifying traffic in a real-time fashion has been extensively studied in recent years due to its importance in many areas such as network security and network management. Port numbers and packet payload signatures have been widely used in many existing traffic classification tools. They, however, are far away from completed due to the increase of new Internet applications and traffic encryption. In this project we develop machine learning algorithms to learn different Internet traffic behaviors, aiming to detect unseen applications, and thus improving the general classification capability of current network systems.

Botnet Mitigation


Botnets are networks of compromised computers infected with malicious code that can be controlled remotely under a common command and control channel. Recognized as one the most serious security threats on current Internet infrastructure, advanced botnets are hidden not only in existing well known network applications but also in some unknown applications, which makes the botnet detection a very challenging problem. In this project we aim to develop a hierarchical network application-based framework for an automatic discovery of botnets based on a big data driven security analytics platform.


Improving Reinforcement Learning Reward Systems to Enable their use in Network Intrusion Detection

  • Kole Nunley (Current Employer: Software Engineer at Cantina)

Strategy Retention of Neural Networks Across Diverse Environments

  • Walker Sorensen (Mathematics, UMass Amherst) 

Network Security Through Vulnerability

  • Nicholas Saling (Current Employer: Member of Technical Staff at Oracle)


Leveraging Cloud-based Resources for Automated Biometric Identification

  • John Grey (Current Employer: Software Engineer at Fidelity Investments)

  • Aram Taft (Current Employer: Prob. Firefighter/EMT at Mendon Fire Department)

Android Secure Text Encryption

  • Jeffrey Putnam (Current Employer: Software Developer at Liberty Mutual Insurance)

An Intelligent Robotic System for Localization and Path Planning Using Depth First Search

Mongoose, A Novel Lightweight Cross-Platform Botnet Over TOR

Investigating Users’ Activities Behind Social Networking Websites

  • Mark Miller (Current Employer: Application Security Engineer at Amadeus)

  • Anthony Amaral (Current Employer: Web Developer, Harvard Business School)



Mining Botnet Behaviors on the Large-scale Web Application Community

  • Dan Garant (Current Employer: Data Scientist at C&S Wholesale Grocers)

Using Biometrics for User Authentication

  • Greg Prevost (Current Employer: Software Development Engineer at Avid)

Design and Implementation of Proxy Firewalls

  • Ryan Blair (Current Employer: Senior Technician at Bottomline Technologies)

Network Security and Honeynet Technology

  • Corey Austin (Current Employer: Technical Account Manager at Tanium)

Identity Theft: Keeping Personal Financial Entities Safe from Theft

  • Andrew Sutton (Current Employer: Software Engineer at Advisor 360)

Encrypting Your Voice Communication on the Internet

  • Alyssa Marinaccio (Current Employer: Academic Technologist, Wesleyan University)

  • Nicholas Ellis (Current Employer: Solutions Engineer at ALM Works)

  • David Sell (Current Employer: Operations Manager at Google)

Protecting Network Security Against Botnet Attack


bottom of page