5067_dsc_0223a.jpg

Birhanu Eshete

Trustworthy Machine Learning Adversarial Machine Learning Privacy-Motivated Inference Attacks Cyber Threat Intelligence AI Risk Management For Autonomous Vehicles
University of Michigan (Dearborn) Computer and Information Science

About

I am an Associate Professor in the Department of Computer and Information Science at the University of Michigan, Dearborn, where I lead the Data-Driven Security & Privacy Lab (DSPLab). I am also a faculty affiliate at the Michigan Institute for Data Science (MIDAS) at the University of Michigan, Ann Arbor. I am a recipient of the U.S. Department of State Fulbright U.S. Scholar Award (2024-2025), the U.S. National Science Foundation (NSF) CAREER Award (2023), USENIX Security Symposium Distinguished Paper Award (2018), Finalist (top 10) for CSAW Best Applied Security Paper Award in North America (2018), and IEEE ICDS Best Paper Award (2010). My current research focus is on trustworthy machine learning (ML) with emphasis on security, privacy, safety, interpretability, fairness, and the dynamics thereof. In the DSPLab, my students and I aim to improve trustworthiness of ML in the face of targeted adversarial manipulations with security and safety implications ([1], [2], [3], [4]), privacy-motivated inference attacks ([5], [6], [7]), and study ML trustworthiness via the interaction among security, privacy, transparency, and fairness properties of ML in high-stakes applications. We also work on the use of adversarial ML tactics to tackle real-world problems such as Internet censorship (([8], [9]). In the past, I worked on leveraging AI/ML for cybercrime with focus on characterization, detection, and forensics of cybercriminal activities ([10], [11], [12]), and cyber threat intelligence with focus on characterization, measurement, and forensics of cyber attacks including advanced persistent threats ([13], [14], [15]). My research has appeared in top security & privacy venues such as IEEE S&P, ACM CCS, USENIX Security, ISOC NDSS, ACM PETS, ACM ACSAC, IEEE/IFIP DSN, and widely accessible venues such as the Science Magazine. My recent work on AI risk management framework use case for autnonmous vehicles has been included in NIST's Trustworthy and Responsible AI Resource Center. Before joining UM-Dearborn, I was a Postdoctoral Researcher in the Systems & Internet Security Lab at the University of Illinois at Chicago. I earned my PhD in Computer Science from the University of Trento, and my B.Sc. and M.Sc. in Computer Science from Addis Ababa University.

Research Performance Summary

49
Total Papers
2594
Total Citations
20
H-Index
2009-2026
Active Research Span

First Recorded Paper

Birhanu Eshete

Year: 2009

Citations: 0

Venue: N/A

Latest Recorded Paper

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

Year: 2026

Citations: 0

Venue: arXiv preprint arXiv:2601.03429

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

2026
1
2025
2
2023
6
2022
6
2021
4
2020
2
2019
4
2018
3
2017
2
2016
2
2015
1

Publication Venues and Collaboration

Journal, Conference, and Book Publication Breakdown

Conference 31
Journal 0
Book 2

Top Coauthors

Eshete Villafiorita Gjomemo

Research Impact by Period

2025-2026

Period Stats
Papers 3
Citations 0
Avg. Citations / Paper 0
H-Index 0

2020-2024

Period Stats
Papers 18
Citations 275
Avg. Citations / Paper 15.3
H-Index 9

2015-2019

Period Stats
Papers 12
Citations 1892
Avg. Citations / Paper 157.7
H-Index 9

2010-2014

Period Stats
Papers 15
Citations 427
Avg. Citations / Paper 28.5
H-Index 9

2005-2009

Period Stats
Papers 1
Citations 0
Avg. Citations / Paper 0
H-Index 0

Contact and Professional Links

Contact Information

birhanu@umich.edu
3135836669

Detected Research Keywords

Detection Malicious Web Malicious Web Pages Vulnerabilities Web Applications Poirot Aligning Attack Aligning Attack Behavior Attack Behavior Kernel Behavior Kernel Audit Kernel Audit Records Audit Records Cyber Records Cyber Threat