Brian Jalaian

Senior AI Research Scientist / Adjunct Assistant Professor

ARL / Virginia Tech


Brian Jalaian is a research scientist and research lead at ARL and a adjunct research assistant professor at Virginia Tech. He has obtained his Ph.D. from the Bradley Department of Electrical and Computer Engineering in 2016 at Virginia Tech. He has obtained his MS in Electrical Engineering (Network and Communication Systems) and MS in Industrial System Engineering (Operation Research) in 2013 and 2014 at Virginia Tech, respectively. His research interests are optimization, machine learning, and network science.


  • Bayesian Inference
  • Bayesian Deep Learning
  • Uncertainty-aware AI
  • Mathematical Optimization
  • Safe Artificial Intelligence
  • Robust, Resilient and Assured Artificial Intelligence


  • PhD in Electrical Engineering - Network Optimization, 2016

    Virginia Tech

  • M.Sc. in Operation Research, 2014

    Virginia Tech

  • M.Sc in Electrical Engineering - Communication Systems, 2013

    Virginia Tech


Deep Learning & Bayesian Machine Learning


Mathematics & Statistics


Mathematical Programming & Optimization




PyTorch & TensdorFlow


Linux Admin and Networking




Adjunct Assistant Research Professor

Virginia Tech

Jun 2018 – Present Virginia
Co-supervise Ph.D. students. Perform Basic Research.

Research Lead

Internet of Battlefield Things

Jan 2018 – Present Maryland
Responsibilities include:

  • Lead Technical Research Direction on Safe, Robust
  • Conduct basic research Safe, Robust, and Resilient Artificial Intelligence

Research Scientist


Jan 2016 – Present Maryland
Responsibilities include:

  • Perform basic research on uncertainty-aware artificial intelligence
  • Perform basic research on safe, robust, and resilient artificial intelligence

Research Assistant

Virginia Tech

Aug 2011 – Dec 2015 Blacksburg, Virginia
Responsibilities include:

  • Conduct basic research on modeling & optimization
  • Perform basic research on modeling complex network dynamics via mathematical programming
  • Conduct basic research on wireless network optimization

Research Assistant

National University of Singapore

Jan 2008 – Jul 2011 Singapore
Responsibilities include:

  • Conduct basic research on design & development of cognitive radio networks

Recent Publications

Quickly discover relevant content by filtering publications.

URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks

While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues …

Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks

In this paper, we present a general framework for distilling expectations with respect to the Bayesian posterior distribution of a deep …

Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification

In this paper, we consider the problem of assessing the ad-versarial robustness of deep neural network models under both Markov chain …

A Real-Time Solution for Underlay Coexistence with Channel Uncertainty

Underlay coexistence is an effective mechanism to improve spectrum effïciency by having picocells coexist with macrocell on the same …

Attribution-Based Confidence Metric For Deep Neural Networks

We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric …