Job Title: Master Thesis – Adversarial ML
Join our Team

About this opportunity:

The objective of Ericsson Research Area Security is to provide Ericsson business and development units with security competence, architectures, solutions for platforms, networks, and services. Our research covers everything from pure cryptography, secure networking, AI/ML security, service layer and application security, identity management and privacy to methods for development and evaluation of security systems. Our focus is on new concepts and methods, patents, and standardization.

When joining our team at Ericsson you are empowered to learn, lead, and perform at your best, shaping the future of technology. This is a place where you’re welcomed as your own perfectly unique self, and celebrated for the skills, talent, and perspective you bring to the team.

This master thesis project will be hosted by Ericsson Research in Kista and will be part of an international team of world-class researchers with different backgrounds, experiences, with a specialization in Adversarial Machine Learning and network security.

The project will focus on Adversarial Machine Learning and hyperparameter tuning. While a student has the freedom to conduct the thesis project according to their preferred directions and methodologies, it is advised to focus on privacy attacks and Reinforcement Learning techniques.

What you will do:

• Reviewing papers related to Adversarial Machine Learning and hyperparameter tuning.
• Conducting experiments on Machine Learning models with varying security levels to evaluate privacy attacks and their corresponding defenses.
• Demonstrating proof of concept through presentations.

The skills you bring:

• A strong knowledge of machine learning methods.
• Programming skills.
• A good understanding of adversarial machine learning.
• A Master program in computer science, machine learning, or equivalent.