PhD Candidate on EXplainable Data Science using Formal Verification

PhD Candidate on EXplainable Data Science using Formal Verification

Published Deadline Location
18 Mar 14 Apr Nijmegen

You cannot apply for this job anymore.

Browse the current job offer or choose an item in the top navigation above.

Job description

As a PhD candidate, you will work on the project EXplainable Data Science using Formal Verification (EXoDuS), for which Dr Nils Jansen has recently acquired funding. The project is partially funded by the VWDATA programme and the Institute for Computing and Information Science (iCIS) of Radboud University and will be carried out in close cooperation with TNO.
 
The impact of artificial intelligence (AI) on autonomous driving, robot-assisted surgery, and home automation has resulted in an increased reliance on AI systems. In mission-critical applications, the inherent vulnerability of such systems to adversarial attacks poses a serious challenge. We propose to immerse humans in the process of robustifying AI systems against problems such as adversarial learning or data poisoning via formal methods. Formal verification in particular provides tools and algorithms to rigorously assess the correctness of a system.
 
The key element is to enable humans to understand AI-made decisions in an adversarial environment. Decision-making is sufficiently captured by so-called strategies; a neural network, for example, represents a strategy that has been learned. For such strategies, data scientists and system engineers lack tools to answer transparency-related questions.
 
You will use formal techniques and directions such as SMT solving, model checking, and partially observable Markov decision processes. From the AI perspective, you will marry the aforementioned concepts with (convolutional) deep neural networks and decision trees. You will be jointly supervised by Dr Nils Jansen and Dr Guillermo Perez.

Specifications

Radboud University

Requirements

  • you hold an MSc or equivalent degree in a field that is closely related to Computer Science;
  • you have a background either in AI and machine learning or in formal methods. A background in both areas is advantageous;
  • in general, excellent math skills or excellent programming skills (or both) are mandatory;
  • you are able to work both independently and as a team player;
  • you are proficient in English (Dutch is not required).

Conditions of employment

  • employment: 0.8 - 1.0 FTE
  • a maximum gross monthly salary of € 2,972 based on a 38-hour working week
  • the gross starting salary amounts to €2,325 per month, and will increase to €2,972 in the fourth year
  • in addition to the salary: an 8% holiday allowance and an 8.3% end-of-year bonus
  • duration of the contract: 4 years
  • your performance will be evaluated after 18 months. If the evaluation is positive, the contract will be extended by 2.5 years
  • you will be classified as a PhD Candidate (promovendus) in the Dutch university job-ranking system (UFO);
  • you will be able to make use of our Dual Career Service where our Dual Career Officer will assist with family related support, such as child care, and help your partner prepare for the local labour market and with finding an occupation

Are you interested in our excellent employment conditions?

Employer

Strategically located in Europe, Radboud University is one of the leading academic communities in the Netherlands. A place with a personal touch, where top-flight education and research take place on a beautiful green campus in modern buildings with state-of-art facilities.

Department

Faculty of Science
Strategically located in Europe, Radboud University is one of the leading academic communities in the Netherlands. The positions are available in the Software Science group of the Institute for Computing and Information Sciences (iCIS) at Radboud University. Research at iCIS focuses on software science, digital security and data science. Our research mission is to improve the security and reliability of computer-based systems and algorithms through mathematically founded theories, methods and tools. During recent evaluations, iCIS has been consistently ranked as the No. 1 Computing Science department in the Netherlands. Evaluation committees praised our flat and open organisational structure, our ability to attract external funding, our strong ties to other disciplines, and our solid contacts with government and industrial partners. The Software Science group is well known for its contributions to the mathematical foundations of software, formal methods, and functional programming.
 
Further information on The Institute for Computing and Information Sciences (ICIS)
Further information on Commit 2 Data
Further information on Nils Jansen

Specifications

  • PhD positions
  • Natural Sciences
  • 30.4—38 hours per week, temporary
  • max. €2972 per month
  • University Graduate
  • 62.20.19

Employer

Location

Comeniuslaan 4, 6525 HP, Nijmegen

View on Google Maps