In an increasingly interconnected world dependent on technology, two ECE researchers are developing a way to keep computer systems safer from would-be hackers with a new approach that would eliminate security loopholes before they can be exploited. ECE Professors Tian Lan and Guru Venkataramani collaborate on a $1.47M grant from the Office of Naval Research titled: “DIALECT: Communication Protocols Customization via Feature Diagnosis, Lacing, Elimination, Cross-grafting, and Trimming”, to study how customized software packages could individualize security in cyber systems by customizing their protocols which would in turn reduce security risks and foster a more resilient system. While software programs are consistently releasing new updates, new loopholes are inadvertently created as the size of the system swells. Standardized versions of common software, like Microsoft Word or Adobe Flash Player, are running on countless machines, which gives potential aggressors the possibility to inflict widespread damage if hackers discover a backdoor into such widely used software systems. Prof. Lan and Prof. Venkataramani believe system security could be improved with customized versions of essential software that only includes features a specific user or company needs. Prof. Venkataramani and Prof. Lan are developing a way to use machine learning to comb through these kinds of software to detect which parts are being used and which are not. From there, they will be able to create customized packages that cut out redundancies and unused features.
On a related research theme, Professor Howie Huang’s Graph Computing Lab (GLab) takes a holistic approach for modeling and analyzing users and machines in enterprise networks. His research aims to analyze the dynamics of the networks to identify cyberattacks as they happen and prevent new ones from happening. Professor Huang and his students are designing and developing novel graph-based machine learning systems, to not only manage the big data generated by these networks, but more importantly, to understand the contextual and causal relationships between entities and events in such networks. Professor Huang’s lab currently works on the CHASE (Cyber Hunting At Scale) project, sponsored by the Defense Advanced Research Projects Agency (DARPA). Innovating at the intersection of algorithms, systems, and applications, Prof. Huang and his students aim to enable knowledge mining and extraction on top of large-scale networks, delivering critical, actionable knowledge to stakeholders in real time. The outcomes of his DARPA project are innovative methods for precise and effective threat detection in enterprise networks. Prof. Huang believes that ultimately his research efforts will lead to new paradigms in AI, machine learning, cybersecurity, and more.