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.
Abstract:
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
Bookings
This event is fully booked.
No Responses