Cybersecurity

As society becomes more connected to and reliant on modern technology, it also grows more vulnerable to cyber attacks. Business environments present challenges as employees connect to proprietary data via numerous mobile devices. Home life now includes a vast array of devices constantly collecting and transmitting data. CSE research has improved cybersecurity in a broad range of settings—from the detection of abnormal and malicious activity, to the identification of fraud and malware.

Security in today’s world goes far beyond information assurance, encompassing a range of analytic and visualization techniques that rely on high performance computing algorithms. A prominent area of CSE research, emerging graph technology at Georgia Tech has the potential to quickly interact with massive amounts of data and respond in near real time to cyber threats.

Graphs are networks with up to trillions of connections, comprised of interconnected vertices and edges that change over time. In the realm of cyber security, the vertices may represent computers, and the edges represent their interactions. By designing fast theoretic algorithms on large-scale graphs, researchers can produce insights in near real time. Projects such as Georgia Tech’s STINGER offer an open-source way to understand data with large, streaming graphs.

In addition to advancing data analysis, we are also actively researching computer architectural requirements to maximize the performance of graph analyses across a variety of problem types. How can we integrate across different algorithms, programming models and architectures to address new challenges? The research includes exploring how best to combine cloud computing with in-memory parallel computing. This work lays a foundation to take on some of the most difficult problems in the world today, from computational biology and genomics, massive-scale data analytics with a focus on parallel algorithms, to combinatorial optimization, and vast social networks.

Our research can be applied to developing enterprise-level computing platforms that are more resistant and adaptive to cyber attack, and that can help organizations stop or predict attacks to protect customers and our nation’s critical infrastructure.