Dong Hyun Jeong
University of the District of Columbia, DC·Computer Science
Computers increasingly help people make high-stakes decisions, from flagging cyberattacks to detecting tumors. But they are often unsure, and that uncertainty is easy to misread.
- Fields
Computer Science
Engineering
Mathematics & Statistics
- Topics
cybersecurity
network security
threat detection
- Grants
- 2 known grants, through Sep 2028
What they work on
- Extract time-, location- and context-aware features of network activity to predict event frequencies and estimate cyberattack severity.
- Generate interpretable, data-driven rules linking network features to attack behaviors, and use them with reinforcement learning to prioritize alerts and recommend incident reviews.
- Design multi-scale temporal visualizations that show security analysts how attacker behavior and risk levels change over time, with quantified confidence.
- Quantify multiple types of uncertainty with belief theory and build them into a unified neural network framework for decision-making under adversarial attack.
- Test uncertainty-aware deep learning designs against intelligent attackers using deception tactics, using simulation models and visualization tools.
More about the research
These two projects combine machine learning with visualization so that people can see how much to trust an automated judgment. One measures the different kinds of uncertainty inside deep learning models. The other builds an early-warning system that ranks network threats by risk.
Why it matters
Security analysts face floods of alerts. AI systems can make dangerous mistakes when they misjudge their own uncertainty. Interpretable risk indicators and alert prioritization could help analysts protecting critical infrastructure, businesses and personal data respond to the most serious threats first. Uncertainty-aware deep learning could make AI more trustworthy in areas such as autonomous driving, medical diagnosis and phishing detection.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Feng Chen
University of Texas at Dallas, TX·Computer Science
Develop online fairness-aware deep learning models for changing data streams, using causal representation learning, differentiable architecture search and online meta-learning, and release open software.
Xinyu Xing
Northwestern University, IL·Computer Science·Early-career
Train adversarial agents that act in a target agent's environment to provoke undesired behavior, using explainable AI methods to guide where the attacks focus.
Jun Zhuang
Boise State University, ID·Computer Science
Improve the resistance of quantum neural networks to adversarial attacks, meaning small deliberate input changes meant to fool them, using Bayesian label transition to infer more reliable labels.
The school
University of the District of Columbia: 2 labs on PI Pages, $9M a year on research, 8 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.