November 9, 2022    
3:00 pm - 4:00 pm


Bookings closed


Essex Hall Room 122
401 Sunset Avenue, Windsor, Ontario, N9B 3P4
Map Unavailable

The School of Computer Science is pleased to present…  

MSc Thesis Proposal by: Saroj Dayal 

Comparison of Membership Inference Attacks in Federated Learning 

Date: Wednesday, November 9, 2022 

Time: 3:00 pm – 4:00 pm 

Location: Essex Hall, Room 122 

Reminder: Two-part attendance is mandatory; arrive 5-10 minutes before the event starts – LATECOMERS WILL NOT BE ADMITTED once the presentation begins.



Federated Learning received a lot of interest in its privacy protection feature. Federated Learning models are vulnerable to several inference attacks, like membership inference attacks. In a membership inference attack, an attacker attacks the federated learning model to identify whether specific data samples have been used during the model training. Federated Learning models must be secured, especially during training, to preserve the privacy of the training datasets and to reduce information leakage.

We compared two membership inference attacks in a federated learning environment and checked the effectiveness of the countermeasures on them. Additionally, we show through experiments which attack is more efficient with countermeasures while maintaining a comparable level of model accuracy.


Keywords: Federated Learning, Membership Inference Attack, Jacobian Matrix


MSc Thesis Committee:  

Internal Reader: Dr. Shafaq Khan

External Reader: Dr. Jagdish Pathak

Advisor: Dr. Dima Alhadidi




This event is fully booked.

No Responses

Leave a Reply

Your email address will not be published. Required fields are marked *