Coming to campus? Visit this page for important information.

MSc Thesis Defense Announcement of Jonathan Khalil: "Developing a Robust Defensive System against First Order Adversarial Attacks Using Siamese Neural Network Methods"

Monday, December 20, 2021 - 09:30 to 11:00

SCHOOL OF COMPUTER SCIENCE 

The School of Computer Science is pleased to present… 

MSc Thesis Defense by: Jonathan Khalil 

 
Date: Monday December 20th, 2021 
Time:  9:30am to 11:00am 
Passcode: If interested in attending this event, contact the Graduate Secretary at csgradinfo@uwindsor.ca with sufficient notice before the event to obtain the passcode
 
Abstract:  
Deep neural networks (DNN) and convolutional neural networks (CNN) have lately been achieving state-of-the-art performance on a wide range of real-life applications. However, recent work has demonstrated that deep neural networks are vulnerable to adversarial attacks, that is inputs that are almost invariant to the human eye from natural data and yet classified incorrectly by the network. Although adversarial training significantly improves model robustness, it eventually becomes a whack-a-mole game where attackers and defenders are just trying to one-up each other. Recent developments in computer applications make security aspects of machine learning increasingly important. With that in mind, an intuitive research question comes to mind, “How can we build deep neural networks that are robust to adversarial inputs?”.  In this paper I introduce the first ever attempt to detect first order adversarial attacks using Siamese Neural Networks (SNN). 
 
Keywords: Adversarial Attacks, Siamese Neural Networks, GAN, Deep learning, Pairwise learning, Triplet loss 
 

MSc Thesis Committee:  

Internal Reader: Dr Sherif Saad 
External Reader: Dr. Mohammad Hassanzadeh 
Advisor: Dr. Alioune Ngom 
Chair:    Dr. Pooya Moradian Zadeh 
 

 MSc Thesis Defense Announcement  Vector Institute in Artificial Intelligence, artificial intelligence approved logo

 

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca (working remotely)