PhD in Secure and Privacy-Preserving Collaborative Language Models

Aalborg University; København; On-site; DKK 320,000 - 420,000; Full time

Job summary

The Department of Electronic Systems at Aalborg University invites applications for a PhD stipend in secure machine learning within the Electronic and Electrical Engineering programme. The PhD position is funded under the Technical Doctoral School and aims to develop privacy-preserving, secure collaboration for language-model based agents.

The successful candidate will work with the AI:SECURITY LAB and cybersecurity group, focusing on privacy-preserving distributed learning, secure multiparty

Qualifications

• Master's degree required in information engineering, computer science, cybersecurity, software engineering or related fields.
• Strong motivation to contribute to cutting-edge AI and security research.
• Excellent written and verbal English communication skills.
• Ability to work independently and collaboratively in interdisciplinary teams.
• Prior background in privacy-preserving ML, distributed training, large language models, agentic AI, or cryptographic protocols is advantageous but not required.

Responsibilities

• Work on privacy-preserving distributed learning for language models, combining federated learning or decentralized training with differential privacy and secure aggregation.
• Develop cryptographic protection mechanisms for collaborative inference and fine-tuning to keep updates, gradients, and representations confidential.
• Design defenses against model extraction and chain-of-thought extraction attacks in multi-agent settings.
• Explore secure agentic AI where autonomous language agents negotiate, verify, and execute privacy-sensitive tasks without information leakage.

Skills

Privacy-preserving ML

Distributed training

Large language models

Agentic AI

Cryptographic protocols

Education

Master's degree in information Engineering, computer science, cybersecurity, software engineering

Job description

The Department of Electronic Systems at The Technical Faculty of IT and Design invites applications for a PhD stipend in the field of secure machine learning within the general study programme Electronic and Electrical Engineering; as per November 1, 2026, or as soon as possible thereafter.

In electronic engineering, Aalborg University is known worldwide for its high academic quality and societal impact. The Department of Electronic Systems employs more than 200 people, of which about 90 are PhD students, and about 40 % of all employees are internationals. In total, it has more than 600 students in its BSc and MSc programs, which are based on AAU's problem-based learning model. The department leverages its unique research infrastructure and lab facilities to conduct world-leading fundamental and applied research within communication, networks, control systems, AI, sound, cyber security, and robotics. The department plays an active role in transferring inventions and results into applications in close collaboration with industrial partners worldwide. You can read more about the department at www.es.aau.dk.

Your work tasks

AAU cybersecurity group is seeking a highly motivated PhD researcher to join our team focusing on secure and privacy-preserving collaborative language models. This research will address critical challenges that arise when multiple parties jointly train, fine-tune, or deploy large language models in distributed environments while safeguarding both model integrity and data confidentiality. The successful candidate will develop novel frameworks that enable effective collaboration among language model-based agents without exposing proprietary parameters, private training data, or sensitive reasoning traces to untrusted participants.

• Privacy-preserving distributed learning for language models, integrating federated learning or decentralized training schemes with differential privacy and secure aggregation to prevent training data memorization and membership inference attacks.
• Cryptographic protection mechanisms for collaborative inference and fine-tuning, employing secure multiparty computation or homomorphic encryption to ensure that model updates, gradients, and intermediate representations remain confidential throughout the collaborative workflow.
• Defenses against model extraction and chain-of-thought extraction attacks, designing protocols that detect and mitigate adversarial attempts to reconstruct model functionality or steal sequential reasoning paths during multi-agent interactions.
• Secure agentic AI, investigating how autonomous language agents can negotiate, verify, and execute privacy-sensitive tasks while preventing context leakage, state exposure, or unintended information flow through semantic side channels.

The research will be validated through real-world use cases such as cross-organizational knowledge sharing, confidential healthcare analytics, and collaborative threat detection, with the goal of producing a coherent framework that balances strong security guarantees against computational feasibility and model utility.

We are looking for a candidate with the following competences:

• Master's degree in information Engineering, computer science, cybersecurity, software engineering, or related fields
• Strong motivation to contribute to cutting-edge research in AI and security.
• Excellent written and verbal communication skills in English.
• The ability to work independently and collaboratively within interdisciplinary teams.
• Prior background in privacy-preserving machine learning, distributed training, large language models, agentic AI, or cryptographic protocols is advantageous but not a requirement

Qualification requirements

PhD stipends are allocated to individuals who hold a Master's degree. PhD stipends are normally for a period of 3 years. It is a prerequisite for allocation of the stipend that the candidate will be enrolled as a PhD student at the Technical Doctoral School of IT and Design in accordance with the regulations of Ministerial Order No. 1039 of August 27, 2013 on the PhD Programme at the Universities and Certain Higher Artistic Educational Institutions. According to the Ministerial Order, the progress of the PhD student shall be assessed at regular points in time.

Who we are

The PhD student will work in cybersecurity group and we also expect close collaboration with the AI:SECURITY LAB in Aalborg University.

The Cybersecurity group in the Department of Electronic Systems has around 20 staff including faculty members, Postdoc researchers, PhD students and Research Assistants. The group has a broad expertise in all topics related to cyber security and machine learning such as network security, cryptography, secure computation, and machine learning security etc.

The AI:SECURITY LAB is part of the AI:X initiative with four PhD stipends and is a collaboration between the Department of Electronic Systems and the Department of Computer Science, at the Technical Faculty of IT and Design. The lab is part of a growing research environment broadly in the area of AI Security, and is expected to grow to approx. 10 PhD students in the next year. We address all topics related to (Cyber)Security in AI; particularly in Natural Language Processing (NLP).

We hold regular seminars to encourage open discussion and constructive feedback. Psychological safety is central to our group, ensuring that every member can propose new ideas, ask challenging questions, and discuss difficulties without fear of negative judgment. We value diverse viewpoints and offer individualized mentorship that balances support with independent growth, creating an environment where rigorous research and mutual respect go hand in hand.

Do you have any questions?

If you have any questions about the position, you are more than welcome to contact us. You will find contact persons at the bottom of the jobpost.

Further information

Read more about our recruitment process here.

The assessment of candidates for the position will be carried out by qualified experts.

Shortlisting will be applied. This means that after the application deadline, the head of the department, with the assistance of the hiring committee, will select the applicants to be assessed. All applicants will be informed whether they have been shortlisted for assessment or not.

The hiring process at Aalborg University may include a risk assessment as a tool to identify potential risks associated with new hires, ensuring the safety, compliance, and integrity of the workplace.

Read more about The Technical Doctoral School of IT and Design

Salary and terms of employment

The employment is in accordance with the Ministerial Order on the Appointment of Academic Staff at Universities (the Appointment Order) and the Ministerial Order on Job Structure for Academic Staff at Universities (in Danish).

Salary and terms of employment are in accordance with the collective agreement between the Danish Confederation of Professional Associations and the state (AC collective agreement) (in Danish).

Aalborg University - Knowledge for the world

Aalborg University is an international workplace with more than 3,700 employees. We offer real-world-oriented education and create world-class research results through collaboration between researchers, students, and public and private companies. This is how we achieve insights, new solutions to societal problems, and knowledge that changes the world. Our main campus is in Aalborg, but we also have campuses in Esbjerg and Copenhagen.