On this page you can find our offering for semester projects. Students who are interested in doing a project are encouraged to have a look at the Thesis & Project Guidelines from the MLO lab, where you will gain an understanding about what can be expected of us and what we expect from students.
Last Update: 31st May 2023
Please, apply via Google form. You will need to specify which project(s) you are interested in, why you are interested, and if you have any relevant experience in this area. To access the form you need to login with your EPFL email address.
We process students in two rounds. We collect applications for projects for the first round until 15th June 2023. We will get back to you about your application in the first week after the deadline. If we do not get back to you during the indicated period, this means that we unfortunately did not have space.
We will leave the form open for late applications. If by 1st September 2023 there are still projects open we will consider all applications submitted by then. We strongly recommend that you apply as soon as possible for best consideration. We expect many projects to be taken after the first round.
External students: Students who are not from EPFL should get in touch with the supervisors of the project(s) via email.
Early deadline: 15th June 2023
First Contact with Supervisors: 19th June 2023 - 30th June 2022
Late deadline: 1st September 2023
First Contact with Supervisors: 4th September 2023 - 15th September 2023
If you encounter any technical issue please get in touch with Laurent Girod.
In this project, the student is expected to look at Machine Learning technologies (i.e. either published research papers or frameworks released on github) that claim to be privacy-preserving and implement privacy attacks. The project can be either research oriented or implementation oriented, depending on the interest of the student.
Requirements
Applying to this project
This semester project is aimed at one/two MSc student/s. The student/s will work with Mathilde Raynal.
Note: Other labs with cool projects on Machine Learning (we can always consider co-supervision):
End-to-end encrypted (E2EE) chat applications, e.g., Signal, prevents the server from peeking into the content of messages. Hence, it restricts server-side censoring, e.g., by dropping messages that contain certain keywords. However, E2EE chat applications are banned and illegal to use in some countries. Citizens can only use non-E2EE chat applications which have a client-server-client architecture. In such a system architecture, the server can easily filter out, and hence, drop any message according to certain criteria. It happened in reality that, shortly after a social incident, users cannot receive any messages, files, or comments about this incident. Yes, this happened.
In this project, we will explore the possibility of circumventing censorship in the context of non-E2EE chat applications. There are several interesting directions: What is the mechanism behind large-scale and real-time keywords filtering? What are the possible ways of circumventing this kind of censorship? How can we lower the barrier for average users to circumvent the censorship and discuss their real thoughts?
Requirements
Applying to this project
This semester project is aimed at one BS/MSc student. The student will work with Boya Wang.
These last years, chat bots became increasingly present on some social network and messengers, particularly in the Russian speaking sphere. These bots mimic real people in public discussions, likely with the purpose of orienting them in directions intended by their author. The goal of the project is to design measures and instruments helping to detect / automatically ban these bots.
Requirements
Applying to this project
This semester project is aimed at one MSc/BSc student. The student will work with Klim Kireev.