Birhanu EsheteRESEARCHER · EDUCATOR · AUTHOR
COMPUTER SCIENTIST · EDUCATOR · AUTHOR

AI should earn
our trust.

I’m Birhanu Eshete. My research makes AI behavior traceable, its vulnerabilities visible, and its decisions more accountable.

University of Michigan–Dearborn
Associate Professor of Computer Science
Birhanu Eshete
RESEARCH WITH PURPOSE

AI Security, Privacy, Safety,
Interpretability, and Ethics
with Human Agency.

A HUMAN VIEW OF AI
SELECTED RECOGNITIONS

NSF CAREER Award

Fulbright U.S. Scholar

USENIX Distinguished Paper

Advancing AI.
Keeping people at the center.

AN AILEPHANT IN THE ROOM
An AILEPHANT in the Room — book cover

An AILEPHANT in the Room

AI’s Promise, Its Perils, and The Future We Must Choose brings this work into a broader public conversation about opportunity, risk, accountability, and the choices that remain in our hands.

Amazon preorder link coming soon.

Explore the book & read the preface

I work at the intersection of Security, Privacy, Safety, Interpretability, and Ethics with human agency.

I am an Associate Professor of Computer Science at the University of Michigan–Dearborn, where I lead the Data-Driven Security & Privacy Lab and direct the Cybersecurity Center for Education, Research, and Outreach. I am also a faculty affiliate of the Michigan Institute for Data & AI in Society at the University of Michigan, Ann Arbor.

My research identifies, explains, and mitigates security, privacy, safety, transparency, and ethical risks in AI. I develop methods to trace how data and computation shape model behavior, detect adversarial manipulation, and diagnose and repair failures. This work addresses high-stakes applications in autonomous systems, healthcare, finance, and cybersecurity.

My contributions have been recognized with the NSF CAREER Award, the Fulbright U.S. Scholar Award, the Faculty Research Excellence Award from the College of Engineering and Computer Science, and the USENIX Security Distinguished Paper Award. My research appears in leading security, privacy, and AI venues, has been featured in Science, and has contributed to the NIST Trustworthy & Responsible AI Resource Center.

Research and teaching across the United States, Europe, and Africa inform my perspective on who benefits from AI, who bears its risks, and who can shape its development. I earned my PhD at the University of Trento and my M.Sc. and B.Sc. at Addis Ababa University, completed postdoctoral research at the University of Illinois Chicago, and returned to Addis Ababa University as a Fulbright Scholar.

In keynotes, seminars, interviews, and teaching, I connect technical research with the decisions facing researchers, educators, and organizational leaders. I welcome research collaborations on trustworthy AI and speaking invitations on AI security, responsible deployment, education, and the preservation of human agency.

Read my full CV
2024–present

Associate Professor

University of Michigan–Dearborn

2024–2025

Fulbright U.S. Scholar

Addis Ababa University

2018–2024

Assistant Professor

University of Michigan–Dearborn

2014–2018

Postdoctoral Researcher

University of Illinois Chicago

Make AI’s behavior
Traceable. Testable. Trustworthy.

Visit DSPLab

I develop methods to uncover and reduce AI risks—from poisoned training data to privacy leaks—with provenance as a foundation for understanding how models behave.

Security & robustness

Understand adversarial manipulation, detect backdoors, and build defenses that withstand hostile inputs.

Privacy & transparency

Protect sensitive data while making model decisions more interpretable and accountable.

Safety & responsibility

Connect technical assurance with the conditions needed to deploy AI responsibly.

Research impact on Google Scholar

Explore my citation record, h-index, and complete publication history.

View publications & citations

From research
to evidence.

Membership leakage profiling feeds privacy-hardening transformations for explanation methods.
System overview · View full-size figure

DeepLeak

Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

Lightweight hardening reduced membership leakage by up to 95%, with at most 3.3% explanation-utility loss on average in the evaluated image benchmarks.

Inference provenance graphs are extracted and characterized to generate and evaluate targeted model repairs.
System overview · View full-size figure

DeepProv

Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis

Tracing inference behavior enables targeted repair: modifying just one network layer improved adversarial accuracy by 55% on average in the evaluated case studies.

Training provenance capture and analysis produce aggregated poisoning scores for detecting suspect samples.
System overview · View full-size figure

PoisonSpot

Precise Spotting of Clean-Label Backdoor Poisoning via Fine-Grained Training Provenance Tracking

Following each training sample’s influence on parameter updates exposes clean-label backdoors that can hide behind apparently legitimate labels.

Trustworthy AI
Learn beyond accuracy.

One of the early university courses dedicated to trustworthy AI, taught by Birhanu Eshete at University of Michigan–Dearborn in Winter 2024.

A complete course at the intersection of robustness, transparency, and accountability.

Recognition for
research that holds up.

Academic profile
2024–2025

Faculty Research Excellence

College of Engineering and Computer Science, University of Michigan–Dearborn

2024–2025

Fulbright U.S. Scholar Award

U.S. Department of State

2023

NSF CAREER Award

U.S. National Science Foundation

2018

Distinguished Paper Award

USENIX Security Symposium · NAVEX

AN AILEPHANT IN THE ROOM · BIRHANU ESHETE
An AILEPHANT in the Room — front cover

Front cover

Read the complete preface.

An AILEPHANT
in the Room

AI’s Promise, Its Perils,
and The Future We Must Choose

A clear-eyed conversation about AI’s possibilities, the harms already here, and the choices still in our hands. Written with a global lens, the book asks who benefits, who bears the risks, and how we preserve human agency.

“The unit of success is not model size.
It is durable human capability.”

Discovery, education, creativity, and development: where AI can expand access to expertise and human capability.

Amazon preorder link coming soon.

Discuss the book

Beyond the paper.
Talks, interviews & podcasts.

State of the Model

BIC Village · DEF CON 30

Promising progress and remaining challenges toward trustworthy machine learning.

Watch talk

Reckoning with AI’s Trust Issues

University of Michigan–Dearborn Reporter

A conversation on the challenges behind reliable and responsible AI.

Read interview

Cybersecurity while working at home

WXYZ Detroit

Practical ways to strengthen cybersecurity beyond the office.

Watch interview

Machine Learning for Environment with Bad Actors

New Frontiers Podcast

A discussion of machine learning in adversarial environments.

Listen to episode

Attacks on Machine Learning

Science Magazine Podcast

The security challenges facing machine learning systems.

Listen to episode

Adventures with Cybercrime Toolkits: Insights for Pragmatic Defense

USENIX Enigma · San Francisco

How lessons from exploit kits can inform reactive, proactive, and counter-offensive strategies against adaptive cybercriminals.

Watch talk & view slides

Invite a talk.
Start a collaboration.

Share your event, audience, or collaboration idea.

Speaking & collaboration inquiry

Booking requests are addressed to birhanu@umich.edu. Your email app opens with the completed inquiry; send it there to submit.

Front cover
Book preview page