Master Thesis - Adversarial Machine Learning Using Model Explanations

Posted date:  Sep 13, 2022
Location: 

Stockholm, Stockholm, Sweden

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, ML/AI 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.

Our Exciting Opportunity

This master thesis project will be hosted by Ericsson Research in Kista and will be part of an international team of researchers with different backgrounds, experiences, with a specialization in adversarial machine learning and network security.

The focus of the project will be on adversarial machine learning attacks using model explanations. In this study, the research on the privacy risks of model explanations will be done on image and/or network traffic datasets that are widely used, moderately complex, and have own labels. A student will have the freedom to conduct the thesis according to own methodology but is advised to focus on membership inference attacks.

 

What you will do

 

  • Study papers related to the attack mechanisms using interpretability against training data extraction attacks and its defense techniques.
  • Implement one membership inference attack.
  • Implement at least one defense method using existing library.
  • Perform experiments on machine learning models with different security levels to evaluate the attack.
  • Present the outcome and write thesis paper.

 

You will bring

 

We are looking for a student studying master program in computer science, machine learning or equivalent. A student must have strong knowledge in deep learning methods and programming skills. Good understanding of adversarial machine learning is a merit.

Applications should include a brief personal letter and CV. Relevant experience is highly valued so please describe accomplished projects and your role in the respected projects. Candidates are encouraged to send in their application as soon as possible. Suitable applicants will be interviewed as applications are received.

 

Why join Ericsson?

 

At Ericsson, you´ll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what´s possible. To build never seen before solutions to some of the world’s toughest problems. You´ll be challenged, but you won’t be alone. You´ll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.

 

What happens once you apply?

 

Click Here to find all you need to know about what our typical hiring process looks like.

Feel free to apply and include a resume in English, outlining how you meet the specific requirements of the position.

The selection and interview process is ongoing. Therefore, send in your application in English as soon as possible.

 

Location: Stockholm, Sweden.

 

If you have any further questions, you are welcome to contact us.

Recruiter: Murat Aydinay (murat.aydinay@ericsson.com).

 

Security clearance including references and relevant background screening will be conducted for final candidates.

Please note that we do not accept applications sent via e-mail.

We welcome the opportunity to meet you!

Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we nurture it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team.

Ericsson is proud to be an Equal Opportunity and Affirmative Action employer, learn more.

Primary country and city:  Sweden (SE)   ||  Sweden : Stockholm : Stockholm  
Req ID: 694048  

Be where it begins

Our Culture

Welcome to an inclusive, global company where your opportunity to make an impact is endless. Share your most innovative ideas, bring your unique perspective and bring your unique perspective in a speak up environment. With us, you will no longer be dreaming of what the future holds – you will be redefining it at a company where you’re empowered to lead and perform at your very best.

Learning and Development

Being a part of our team means having the flexibility to take your career in many different directions, but it also means leveraging the supportive structure of a big organization, with clear personal and professional development opportunities. 

Benefits and Rewards

We believe that great accomplishments deserve great benefits and transparent rewards. We strive to offer competitive, unbiased, and fair rewards for all our people. We empower you to manage your own time and promote flexible working opportunities, along with family-friendly policies.

Click here to find out more about our benefits.


Job Segment: Computer Science, Network Security, Learning, Security, Technology, Human Resources