PhD position in Network Security for Distributed AI

Publiceringsdatum: 2025-06-27

En möjlighet har öppnat upp för dig att börja arbeta som doktorand hos Chalmers Tekniska Högskola AB. Vill du arbeta heltid hos Chalmers Tekniska Högskola AB? Just nu letar de efter någon som vill ha en tjänst 6 månader eller längre. Arbetsplatsen ligger nära tillhands om du är bosatta i Göteborg som är tjänsteorten.

Chalmers Tekniska Högskola AB söker efter fler duktiga individer som vill arbeta som doktorand. De har just nu ett ledigt jobb som doktorand som kan vara av intresse för dig. Har du vad som krävs för att arbeta som doktorand hos Chalmers Tekniska Högskola AB? Ansök innan tisdag den trettionde september 2025 och ta reda på det!

Jobbannons

This PhD project focuses on strengthening network security for large-scale distributed AI training. As training increasingly spans multiple data centers connected over wide-area networks, it introduces new and underexplored vulnerabilities to network-based threats. The goal of this research is to uncover such threats, evaluate their impact on training performance and model integrity, and develop cross-layer defenses that ensure secure and efficient AI model development at scale.

Information about the division

The department of Computer Science and Engineering is strongly international, with approximately 300 employees from over 30 countries. The department is a fully integrated department with Chalmers University of Technology and University of Gothenburg as principals. The position is placed in the Division for Computer network and systems and the employment is placed with Chalmers University of Technology.

Our research spans from theoretical computer science to applied systems development. We provide high-quality education at the bachelor's, master's, and doctoral levels, offering over 120 courses each year. We also have extensive national and international collaborations with academia, industry, and society.

The PhD position will be placed in the Secura Lab led by Assistant Professor Muoi Tran. Dedicated to advancing the field of Network Security, Secura Lab focuses on innovative solutions to protect modern digital infrastructure from emerging network threats. Despite being young, Secura Lab has an excellent track record in publishing at top-tier security and blockchain conferences. At Secura Lab, we strongly believe a healthy work-life balance is the key to our research excellence. Please visit our website for a letter to prospective students.

Project description

Artificial Intelligence (AI) has gradually become a cornerstone of modern life. Its success depends on immense computational effort and extended training times to produce sophisticated models. To handle the scale of these models, distributed AI training has emerged as the standard approach, which utilizes thousands of high-performance devices within a data center to collaboratively process tasks. When they are even more complex, the training infrastructure must eventually scale beyond a single data center, requiring communication between multiple data centers over Wide Area Networks or the Internet. Such communication exposes the training process to several network threats, such as DDoS attacks, traffic hijacking, and traffic analysis. While these risks are well-studied in existing literature, their impacts on distributed AI training, unfortunately, remain largely unexplored. This project envisions Bifröst, secure networks built for distributed AI training. Our objectives include identifying novel network attacks against distributed AI training systems. Furthermore, we aim to develop a measurement framework to assess the impact of such attacks on training performance, adversary costs, and model accuracy. Our ultimate goal is to design a generalized, cross-layer defense framework that integrates network-level mitigation and application-level optimization to comprehensively protect distributed AI training from network threats while maintaining competitive performance.

This position is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP). WASP is Sweden’s largest individual research program ever, a major national initiative for strategically motivated basic research, education and faculty recruitment. The program addresses research on artificial intelligence and autonomous systems acting in collaboration with humans, adapting to their environment through sensors, information and knowledge, and forming intelligent systems-of-systems. The vision of WASP is excellent research and competence in artificial intelligence, autonomous systems and software for the benefit of Swedish society and industry

Who we are looking for: 

• To qualify as a PhD student, you must have a Master's degree (masterexamen) of 120 credits or a Master’s degree (magisterexamen) of 60 credits in computer science, computer engineering, electrical engineering, or another relevant field* 
• You will need strong written and verbal communication skills in English 
• Excellent grades in computer networks, distributed systems, or cybersecurity courses
• Strong programming language skills
• for students with an education earned outside of Sweden, a 4-year Bachelor’s degree is accepted. 

The following experience will strengthen your application: 

• Familiarity with Federated Learning

We value a collaborative attitude and an interest in working both in teams and independently. Self-motivation, attention to detail, and problem-solving analytical ability are important personal qualities for this position.

What you will do: 

• Take courses at an advanced level within the Graduate school of Computer Science and Engineering
• Develop your own scientific concepts and communicate the results of your research verbally and in writing 
• The position generally also includes teaching on Chalmers' undergraduate level or performing other duties corresponding to 20 percent of working hours 
• Successful candidates will be enrolled, in addition to the department’s PhD program, to the WASP graduate school. The graduate school within WASP is dedicated to provide the skills needed to analyze, develop, and contribute to the interdisciplinary area of artificial intelligence, autonomous systems and software. lecturers, the graduate school actively supports forming a strong multi-disciplinary and international professional network between PhD-students, researchers and industry.

To read more about contract terms and what we offer, please click here.

Application procedure 

To read more and apply, please click here to go to Chalmers vacancy page. 

We welcome your application no later than September 30th, 2025.

For questions, please contact:  

Muoi Tran

Email: muoi@chalmers.se 

Tomas Olovsson

Email: tomas.olovsson@chalmers.se

We look forward to your application!