PhD in Secure and Privacy-Preserving Collaborative Language Models

Aalborg Universitet; Denmark; On-site; DKK 312,000 - 402,000; Full time

Job summary

Aalborg University’s Department of Electronic Systems invites applications for a PhD stipend in secure machine learning within Electronic and Electrical Engineering, starting Nov 1, 2026 or as soon as possible.

The department is renowned for its AI, security, and cyber research, with a strong international environment and collaborations across faculties. The PhD position emphasizes privacy-preserving language models, distributed training, and cryptographic protections.

Qualifications

• Master's degree or equivalent in a relevant field and strong motivation for advanced AI security research.
• Excellent written and verbal English communication skills.
• Ability to work independently and in interdisciplinary teams.
• Prior background in privacy-preserving machine learning or cryptographic protocols is advantageous but not required.

Responsibilities

• Join the cybersecurity group focusing on secure and privacy-preserving collaborative language models.
• Develop frameworks for privacy-preserving collaboration among language-model agents.
• Explore federated/distributed learning with secure aggregation and cryptographic protections.
• Investigate defenses against model extraction and semantic leakage in multi-agent systems.

Skills

Motivation for research in AI and secu

English communication

Independent and collaborative work

Privacy-preserving ML (advantage)

Education

Master's degree in information engineering / computer science / cybersecurity / software engineering

Job description

The Technical Faculty of IT and Design, Department of Electronic Systems, Communication, Media and Information technologies

Organisation/Company Aalborg Universitet Department The Technical Faculty of IT and Design, Department of Electronic Systems, Communication, Media and Information technologies Research Field Computer science » Informatics Computer science » Cybernetics Computer science » Other Engineering » Computer engineering Engineering » Electronic engineering Engineering » Other Researcher Profile First Stage Researcher (R1) Application Deadline 4 Oct 2026 - 21:59 (UTC) Country Denmark Type of Contract Temporary Job Status Full-time Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer 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. Specific research topics can include, but are not limited to:

• 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.

Your competencies

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.