Natan Levy
I am an artificial intelligence researcher, and a Ph.D. Student at the School of Computer Science and Engineering at the Hebrew University of Jerusalem. My advisor is Dr. Guy Katz and I am part of the Katz Lab.
My research focuses on the robustness and verification of machine-learning models deployed on safety-critical systems.
I have more than twenty years of experience in Software and System Engineering in various roles and applications.
Education
My Studies
2020 - Today
Hebrew University, Ph.D. student, Computer Science.
2014 - 2016
Technion, Master of System Engineering.
2003-2005
Ben Gurion University, MBA.
1995-1999
Open University, BA, Computer Science (Graduated with honors)
Publications
Paper
DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace
G Katz, N Levy, I Refaeli, R Yerushalmi
Arxiv Technical Report, Dec. 2023
My Experience
Roles & Responsibilities
2018 - Today
Head of Software Tools, Methods, and Engineering Processes, Defence Company
Leading 3 Software Engineers teams (20 employees): DevOps and SW tools, SW & System quality, and System & SW methodology, supporting hundreds of engineers in the group. Reported directly to head of engineering, as part of the engineering staff.
2012 - 2018
System Engineer, Defence Company
Leading airborne System & Software design for retrofitting an existing product for formal software certification with DO-178C. Applied my deep knowledge and abilities to product delivery.
1999-2012
Software Engineer, Variety of Companies
My experience has been in the field of system and software engineering for a variety of organizations, including Intel, ECI, Amdocs, and others. I have a wide range of expertise in autonomous vehicles, optimizing, recording systems, radio frequency fusion, embedded real-time, Windows APIs, and databases.
My Volunteer Background
Philanthropic Engagements
2015- Today
SpaceIL - Education Team
Volunteer in the Education Team of SpaceIL, developer of the Beresheet lunar spacecraft, sent to the moon, to create inspiration among children and encourage STERN education.
And More
As part of the annual ITforIDF conference, I was given an opportunity to present my own research on the weaknesses of AI, adversarial examples, formal verification, and adversarial models during the panel discussion.