The problem of insider threat detection has been studied for a long time, but the traditional machine learning-based detection approaches, which heavily rely on feature engineering, do not accurately capture the behavior difference between malicious insiders and normal users due to the dynamic and adaptive nature of insider threats.  

This project – led by Utah State University – develops a deep learning framework for insider threat detection by developing self-supervised user behavior representation learning, few-shot learning for malicious session detection, reinforcement learning for adaptive behavior detection, and counterfactual explanations based malicious activity detection. The project’s broader significance and importance are to provide a novel toolset for detecting and mitigating internal security risks, which can benefit industries and governments, which are frequently under attack from malicious insiders. 

Cryptography has shown itself to be invaluable in everyday life, especially as more and more devices and interactions are moving to the online world. Even though users -- often unknowingly-- rely on the security of systems that use cryptography, recent years have seen a number of serious vulnerabilities in the cryptographic pieces of systems, some with large consequences. These have been caused by various problems, including poor designs, difficulty of implementation, and use -- or misuse -- of (in)secure primitives. Cryptographic automation is a relatively new and promising area that is designed to help solve many of these issues and make developing secure systems far easier and less error-prone, even for a non-expert.  

This project – led by Purdue University – focuses on removing the human element from the deployment and analysis of cryptographic systems. Using cryptographic automation and the development of tools, the project aims to make it easier to design and securely deploy new and complex cryptographic systems while preventing insecurities from occurring in such systems.  

Biometrics technology related to recognizing the identities and traits of people has been widely adopted in intelligence gathering, law enforcement, and consumer applications. Recent studies suggest that face-based biometric technology does not work equitably across demographic variations. There is a pressing need to investigate fair biometric solutions and modalities toward accurate, fair, and trustworthy technology for enhanced security and public safety. Ocular biometrics, which consists of regions in and around the eyes, offers an alternate solution to face biometrics due to its accuracy and privacy.  

This project – led by Wichita State University – investigates the fairness of ocular biometric technology and develops solutions to mitigate unequal accuracy gaps across demographic variations. This project spans a highly multidisciplinary research area, which integrates engineering, statistics, mathematics, computing, and policy. The findings of this project are used to update the engineering curricula, including computer vision, image analysis, machine learning, deep learning, and biometrics.  

Josiah Hester, Ph.D., is the Breed Chair of Design and assistant professor of Computer Engineering at Northwestern University, who currently works toward a sustainable future for computing influenced by his Native Hawaiian (Kanaka maoli) heritage. In 2021, Dr. Hester received many accolades and awards including American Indian Science and Engineering Society's Most Promising Engineer or Scientist Award and 3M Non-tenured Faculty Award. He was also named one of Popular Science's Brilliant Ten.