PhD Student in the Distributed Systems Group
Updated: 26 Nov 2019
While distributed machine learning, e.g., training neural nets on distributed and decentralize machines, is becoming the core of today's artificial intelligence, concerns of network resilience ever increase. Distributing the algorithm on multiple nodes individual nodes or communication links between nodes might fail or be attacked. Potential consequences are delays, incomplete results, or even incorrect solutions. It is essential for the wide-spread adaption of distributed machine learning to i) quantify the effect of such failures and attacks, and ii) provide suitable protection mechanisms.
In this project, the PhD student shall first design realistic failure and attacker models, evaluate the effect of these failures and attacks, and design defenses that increase the resilience of machine learning in distributed and decentralized systems.
The applicant should have a Master degree (or equivalent) in computer science or a related field. Specifically, the project requires a strong background in security, preferably network resilience or network security. In addition, experience in machine learning, statistics, and distributed systems is an advantage. Furthermore, the candidate should have excellent communication skills, the ability to work independently, and a strong drive to conduct outstanding research.
The TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. Coming to Delft Service organizes diverse events for new international employees and their accompanying partners, like Partner Career Workshops and Dutch Culture Workshops. Located on campus are the International Children’s Centre and an international primary school which are subject to availability as well as several bilingual schools in the nearby surrounding. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.
38 - 40 hours per week