Computer Science Seminar

  • December 2, 2022
  • 1:20 PM - 1:30 CST
  • Doyle Center Lower-Level space
  • Mohammed Abuhamad, mabuhamad@luc.edu
  • Open to the public.
  • Add to calendar
  • Details

    Hi everyone,

    The Computer Science Department will host a CS Seminar event next Friday, December 2nd, featuring an exciting talk by Dr. James C. Davis (Purdue University). Please RSVP your attendance to this event to enjoy a meal, social, and the main talk by Dr. James C. Davis. Thank you, and we'll see you there! - Mohammed

    Schedule:
    12:00 - 12:45 PM - Lunch and Social
    12:45 - 01:30 PM - Talk by Dr. James C. Davis (Purdue University)

    Speaker and Talk:

    Towards a trustworthy pre-trained neural network supply chain
    Talk By: Dr. James C. Davis

    Abstract:
    Deep neural networks are widely used in computing systems, from image recognition in autonomous vehicles to detecting anomalies in system logs. Creating and specializing neural networks is growing more difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to exchange and reuse pre-trained neural networks (PTNNs). When re-using a PTNN, an engineer can focus on fine-tuning it for downstream tasks. Understanding this software engineering process is the first step to optimizing and securing it, e.g. through model search engines for reuse, improved testing techniques for validation, and better definitions for PTNN packaging. However, the details of real-world PTNN reuse remain unknown. In this talk, I present results from the first empirical software engineering projects to define the PTNN supply chain and evaluate aspects of trust in this context.

    Speaker Bio: James C. Davis is an assistant professor of Electrical and Computer Engineering at Purdue University. He worked for IBM from 2012-2015 and received his PhD degree from Virginia Tech in 2020. His research is in software engineering, with applications in systems and cybersecurity. His work appears at venues such as ICSE, ESEC/FSE, and S&P, and has been recognized with three ACM SIGSOFT distinguished paper awards. His lab is supported by the NSF, Google, Rolls Royce, and Cisco.


    Thanks,

    Mohammed Abuhamad
    Assistant Professor of Computer Science
    Department of Computer Science
    Loyola University Chicago
    308 Doyle Center, Lake Shore Campus
    1052 W Loyola Ave. Chicago, IL 60626
    Email: mabuhamad@luc.edu
    Phone: 773-508-3557
    Web: abuhamad.cs.luc.edu