School of Computer Science Colloquium Presentation by Dr. Adel Abusitta:"AI for Cybersecurity: Building Robust and Sustainable Malware Detection and Classification System”

Date: March 17, 2023

Time: 11:00am – 12:00pm

Location: Erie Hall, Room 3123

Reminders: 1. Two-part attendance mandatory (sign-in sheet, QR Code)

2. Arrive 5-10 minutes prior to event starting - LATECOMERS WILL NOT BE ADMITTED. Note that due to demand, if the room has reached capacity, even if you are "early" admission is not guaranteed.

3. Please be respectful of the presenter by NOT knocking on the door for admittance once the door has been closed whether the presentation has begun or not (If the room is at capacity, overflow is not permitted (ie. sitting on floors) as this is a violation of the Fire Safety code).

4. Be respectful of the decision of the advisor/host of the event if you are not given admittance. The School of Computer Science has numerous events occurring in the near future.

 

 

In the recent years, numerous cyber-security mechanisms have been developed to defend against evolving security threats. However, malware (or malicious software) is still evolving and becoming more sophisticated, and harder to detect and understand. In fact, manual analysis of malware samples is not effective in preventing their harmful impact. Typically, malware samples are variations of existing ones belonging to known malware families. Malware samples within the same family exhibit similar behaviors and often share similar objectives. Therefore, building an effective malware classification system that automatically recognizes the family of a new malware sample is crucial to discern its malicious intent. In this talk, I will talk about the existing malware detection and classification systems. I will also present the proposed AI-powered malware detection and classification system. Our framework addresses two key challenges associated with malware classification: the classification of malware in unstable and changing environments, and the classification of malware with limited and/or incomplete information (sustainability). 

Keywords: AI-powered Malware Analysis, AI for Cybersecurity, Malware Detection, Malware Classification, Deep Learning

 

 

Dr. Adel Abusitta is an Assistant Professor in the School of Computer Science at the University of Windsor. Before joining the University of Windsor, Dr. Abusitta was a Postdoctoral Fellow at McGill University, where he worked on designing and implementing AI-powered data analytics to discern malware intent in collaboration with Defence Research and Development Canada (DRDC). Previously, Dr. Abusitta served as a data-driven cybersecurity researcher and consultant at the Institute for Data Valorization (IVADO). He has mentored graduate students and helped them develop innovative and practical research ideas on topics related to machine learning security and privacy. In addition, he has worked with industrial partners to find best practices for synthesizing sensitive data and achieving privacy-preserving machine learning without compromising accuracy. Dr. Abusitta received his Ph.D. in Computer Engineering (Cybersecurity) from the University of Montreal.