The UMBC Cyber Defense Lab

Machine Learning and Artificial Intelligence: A Technical Chat with the Defense Information Systems Agency

James Curry
Lead Engineer–DoD Cyber Security Range
Defense Information Systems Agency (DISA)

12:00–1:00pm Friday, 28 September 2018, ITE 227, UMBC

A broad reaching brief on the scope and scale of the DISA Mission, followed by a dive into DISA’s efforts to develop Machine Learning and Artificial Intelligence to help defend the nation’s cyber infrastructure. Attendees are highly encouraged to ask questions.

James Curry is the Lead Engineer of the DoD Cyber Security Range (CSR). The CSR’s mission is to replicate the DoD Information Network (DODIN) environment at lab scale, while maintaining high-fidelity realism. As Lead Engineer, Mr. Curry led the design, acquisition, and implementation of two first-of-its-kind technologies: a Virtual Internet Access Point (vIAP) and a Virtual Joint Regional Security Stack (vJRSS). These technologies enable the DoD Workforce to train in an IaaS-on-demand environment that realistically matches DISA’s core infrastructure. Mr. Curry is a Scholarship for Service (SFS) recipient (2008-2009) and received his masters and bachelors of science in computer science from New Mexico Tech. Email: *protected email*

Host: Alan T. Sherman, *protected email*

The UMBC Cyber Defense Lab meets biweekly Fridays. All meetings are open to the public. Upcoming meetings for Fall 2018 include the following.

• Oct 12 Enis Golaszewski, The 2018 UMBC SFS study
• Oct 26 Enis Golaszewski, Using tools in the formal analysis of cryptographic protocols
• Nov 9 Razvan Mintesu, Legal aspects privacy
• Dec 7 Tim Finin, A knowledge graph for cyber threat intelligence

The post Machine learning and AI for cybersecurity: a technical chat with DISA appeared first on Department of Computer Science and Electrical Engineering.

The UMBC Cyber Defense Lab presents

Classifying Malware using Data Compression

Charles Nicholas, UMBC

12:00–1:00pm Friday, 20 April 2018, ITE 229

Comparing large binary objects can be tricky and expensive. We describe a method for comparing such strings, using ideas form data compression, that is both fast and effective. We present results from experiments applying this method, which we refer to as LZJD, to the areas of malware classification and digital forensics.

Charles Nicholas (*protected email*) earned his B.S. in Computer Science from the University of Michigan – Flint in 1979, and the M.S. and Ph.D. degrees in Computer Science from Ohio State University in 1982 and 1988, respectively. He joined the Computer Science Department at UMBC in 1988. His research interests include electronic document processing, intelligent information systems, and software engineering. In recent years he has focused on the problems of storing and retrieving information from large collections of documents. Intelligent software agents are an important aspect of this work. Host: Alan T. Sherman, *protected email*

The UMBC Cyber Defense Lab meets biweekly Fridays. All meetings are open to the public.

The post 🗣 talk: Classifying Malware using Data Compression, 12-1 Fri 4/20, ITE229 appeared first on Department of Computer Science and Electrical Engineering.