Draft:Birhanu Eshete

• Comment: Does not pass WP:NPROF Sohom (talk) 06:06, 31 August 2024 (UTC)

---

Birhanu Eshete
Nationality	Ethiopian-American
Alma mater	University of Trento (Ph.D.) Addis Ababa University (M.Sc., B.Sc.)
Known for	Trustworthy Machine Learning, Adversarial Machine Learning, Privacy-Preserving Machine Learning
Awards	NSF CAREER Award (2023) Fulbright U.S. Scholar Award (2024-2025) USENIX Security Symposium Distinguished Paper Award (2018)
Scientific career
Fields	Computer Science
Institutions	University of Michigan–Dearborn
Website	https://www-personal.umd.umich.edu/~birhanu/

Birhanu Eshete (Amharic: ብርሃኑ እሸቴ) is an Ethiopian-American computer scientist and an Associate Professor of Computer Science at the University of Michigan–Dearborn. He is known for his work in trustworthy machine learning, particularly in enhancing the security, privacy, and fairness of machine learning systems in the face of adversarial threats. He is the recipient of the National Science Foundation (NSF) CAREER Award in 2023 and the Fulbright U.S. Scholar Award for 2024-2025.

Early Life and Education

Birhanu Eshete was born in Ethiopia. He completed his undergraduate and master's degrees in Computer Science at Addis Ababa University. He later pursued his Ph.D. in Computer Science at the University of Trento in Italy. His doctoral research focused on the intersection of cybersecurity and artificial intelligence.

Career

After earning his Ph.D., Eshete worked as a Postdoctoral Researcher in the Systems Internet Security Lab at the University of Illinois at Chicago. He later joined the faculty at the University of Michigan–Dearborn, where he leads the Data-Driven Security & Privacy Lab (DSPLab).

His research focuses on the robustness and trustworthiness of machine learning systems, particularly in the face of adversarial manipulations. His work has been published in top security and privacy conferences, including IEEE S&P, ACM CCS,USENIX Security, and the Science Magazine.

Eshete's work on an AI risk management framework for autonomous vehicles has been included in NIST’s Trustworthy & Responsible AI Resource Center. His research has been instrumental in advancing the understanding of adversarial machine learning and its implications for real-world applications.

Awards and Honors

• NSF CAREER Award (2023)
• Fulbright U.S. Scholar Award (2024-2025)
• USENIX Security Symposium Distinguished Paper Award (2018)
• Finalist for the CSAW Best Applied Security Research Award in North America (2018)

Selected Publications

• Eshete, B. "Making Machine Learning Trustworthy.", Science, 2021.
• Jarin, I., Eshete, B. "MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members. ACM PETS, 2023.
• Amich, A., Eshete, B. "Morphence: Moving Target Defense Against Adversarial Examples.", ACM ACSAC, 2021.

External Links

• Personal Page
• Birhanu Eshete's profile at the University of Michigan
• Science Podcast: Risks of exposing machine learning algorithms online
• Google Scholar Profile
• USENIX ENIGMA Talk on Cybercrime Toolkits