PhD position on ‘Adaptive Privacy and Differential Privacy for Energy Data’

AcademicTransfer; Heerlen; Remote; EUR 429,000 - 544,000; Full time

Job summary

The Open Universiteit invites applications for a PhD position on Adaptive Privacy and Differential Privacy for Energy Data in Heerlen, the Netherlands. You will develop methods combining differential privacy, privacy attacks and privacy-utility optimization within the SHARE project.

Collaboration with Radboud University and Alliander is a core part of the role. The position is fixed-term, 4 years, with a starting salary per month in the Dutch CL) scale and strong training opportunities.

Qualifications

• MSc degree in a relevant discipline as listed; strong background in privacy-enhancing tech.
• Strong programming skills, especially Python.
• Familiarity with deep generative models (VAEs, GANs, diffusion).
• Excellent written and spoken English skills.
• Knowledge of Dutch is preferred but not mandatory.

Responsibilities

• Develop adaptive privacy protection methods for energy data.
• Study privacy attacks and utility metrics on original and synthetic data.
• Balance privacy guarantees with statistical, temporal, and physical utility.
• Collaborate with Radboud University and Alliander researchers.
• Contribute to an open-source privacy layer for the SHARE toolbox.

Skills

Privacy-enhancing tech

Python

Deep generative models

English proficiency

Dutch language (pref.)

Education

MSc in Computer Science, Cybersecurity, AI, Data Science, or related

Tools

VAEs

GANs

Diffusion models

Job description

PhD position on Adaptive Privacy and Differential Privacy for Energy Data

Can you help make energy data usable without giving away sensitive information?The energy transition in the Netherlands urgently requires upgrading of the electricity grid, for instance to accommodate solar panels, wind turbines, and electric vehicles. To efficiently plan and manage these upgrades, stakeholders such as grid operators, municipalities and energy communities need to share detailed data about electricity consumption, generation and grid operation. This data sharing however is prevented by concerns on the competitively sensitive nature and privacy of data, as it reveals detailed information about households, buildings and operational assets. Synthetic data generated by generative AI-models offers a promising alternative, but preserving statistical, temporal, and physical characteristics of real energy data while protecting sensitive information are major challenges. We are offering a PhD position in the SHARE project that addresses these challenges.

As a PhD candidate, you will develop methods for adaptive privacy protection of energy data, combining differential privacy, empirical privacy attacks and privacy-utility optimisation. Your research is part of the Adaptive Privacy and Legal Compliance work package in the SHARE project. More specifically, your challenges are to:

• Investigate how temporal patterns, spatial information, rare events and other distinctive features contribute to re-identification and inference risk. You will work with metrics such as uniqueness, entropy, attack success rates and time-series-specific indicators.
• Implement and study attacks such as membership inference, reconstruction, re-identification and attribute inference to understand where information leakage occurs in both original and synthetic datasets.
• Investigate methods that allocate stronger protection to sensitive components and lighter perturbation to lower-risk components, thereby preserving as much analytical utility as possible.
• Formulate privacy protection as an optimisation problem balancing formal privacy guarantees against statistical, temporal and physical utility requirements for energy-system applications.
• Collaborate closely with researchers at Radboud University, who develop physics-informed generative models for synthetic energy data, and investigate approaches such as differentially private training and post-generation privacy calibration.
• Work closely with distribution system operator Alliander and other consortium partners to evaluate whether the developed methods provide meaningful protection while retaining the information required for practical energy-system applications.
• Ultimately contribute to an open-source privacy layer for the SHARE toolbox.

Requirements

Requirements

You hold, or will soon obtain, an MSc degree in Computer Science, Cybersecurity, Artificial Intelligence, Data Science, Applied Mathematics, or a closely related discipline. You should have:

• a strong background in privacy-enhancing technologies, artificial intelligence, cybersecurity or statistical modelling;
• strong programming skills, particularly in Python;
• preferably, some familiarity with deep generative models (VAEs, GANs, diffusion models) and probabilistic modelling;
• good written and spoken English skills;
• knowledge of Dutch language preferred not mandatory.

Conditions of employment

Fixed-term contract : for 4 years.

The PhD candidate will be appointed for a period of 15 months. The appointment will be extended to 4 years when progress and performance are good. A PhD training program is part of the agreement.

The salary is determined in accordance with salary scale P of Appendix A of the Collective Labour Agreement of Dutch Universities and ranges from € 3.204,-- gross per month upon commencement to € 4.051,-- gross per month in the fourth and final year, in case of full employment.

The Open Universiteit provides good secondary benefits such as training, mobility, part-time employment and paid parental leave.

Station

The position is officially based in Heerlen. As part of the PhD project, you will mainly work at Radboud University in Nijmegen, where you will collaborate closely with the other researchers in the SHARE project. This setup enables close day-to-day collaboration with researchers working on machine learning, synthetic data and energy systems.

You will be employed by Open Universiteit and supervised by Dr. Mina Alishahi as your primary supervisor, with Prof. dr. ir. Harald Vranken as co-supervisor.

Employer

Working at the Open University means contributing to academic education for the most motivated students in the Netherlands and Flanders, as well as to scientific research with visible impact for people and society. With a broad range of bachelor’s and master’s programmes and short courses, the Open University makes lifelong learning accessible to everyone. There are no prior education requirements for bachelor’s programmes: anyone aged eighteen or older can enrol. Education is hybrid and flexible, available anytime and anywhere, at a pace that suits the student.

The majority of the nearly 16,000 students combine their studies with work. This creates a valuable interaction: experiences and questions from professional practice enrich education and research and increase their societal relevance. It is therefore no coincidence that the Open University has ranked in the top three of the Dutch Keuzegids for universities for many years, and this year holds the number one position.

In research, the university focuses on three central themes: healthcare, digitalisation and AI, and society and citizenship. Solutions to today’s challenges are sought across disciplinary boundaries and in collaboration with partners.

The Open University employs approximately 800 staff members, has its main campus in Heerlen, and operates study centres in the Netherlands and Flanders. Its culture is people-centred, collaborative, and inclusive: an environment in which students, staff, and partners feel connected, with ample opportunities for personal development and a healthy work-life balance.

Department

Department of Computer Science

You will be appointed within the Department of Computer Science of the Faculty of Science. The department’s research program Towards high-quality and intelligent software (2020-2025) consists of four research lines, focusing on:

• Techniques for quality assurance of software systems
• Software and computer system security, and privacy-by-design
• Responsible artificial intelligence, including methods and applications of AI
• Educational tools and computing education.