2 University Assistant (Prae-Doc) (# of pos: 2)

Updated: over 2 years ago
Job Type: PartTime
Deadline: 22 Aug 2021

TU Wien is Austria's largest institution of research and higher education in the fields of technology and natural sciences. With over 26,000 students and more than 4000 scientists, research, teaching and learning dedicated to the advancement of science and technology have been conducted here for more than 200 years, guided by the motto "Technology for People". As a driver of innovation, TU Wien fosters close collaboration with business and industry and contributes to the prosperity of society.

As part of the SecInt Doctoral College (SecInt-DK), TU Wien is offering two positions as university assistant (Pre-Doc) for 4 years for 30 hours/week, with an option to upgrade to 40 hours/week. Expected start: September 2021.

The Research Projects: 

We are offering 2 interdisciplinary positions, one for each research project (RP) described below.

Please clearly indicate in your motivation letter which research project(s) you are applying for.

RP4: A Robust Machine Learning Methods for the Detection of Anomalies in Network Traffic

Some machine learning methods are difficult to apply in network security, because they lack explainability and robustness in adversarial environments. The focus of this PhD project is the investigation and development of robust machine learning methods that provide a certain degree of explainability and provide robustness against manipulation in adversarial environments. The objectives of the project are to investigate the suitability of modern machine learning for the detection of anomalies in network traffic, the analysis of methods to manipulate machine learning results to evade detection and exploration of approaches to make machine learning methods robust against manipulation.

The candidate should have experience in network security with focus on network traffic analysis andanomaly detection. Furthermore some background in machine learning and programming is expected.

RP7: Trustworthy Machine Learning

In this project, we will tackle a weakness of several machine learning algorithms that is the more apparent, the more wide-spread their use in critical real-world applications becomes: they can be fooled all too easily. In addition to having low error rates, our algorithms will have a high, well-calibrated confidence in their predictions and guaranteed robustness to malicious manipulations.

You will ideally have a strong background in machine learning, theoretical computer science, and mathematics.


Tasks:
  • Collaboration on current research projects
  • Deepening scientific knowledge
  • Collaboration in academic teaching
  • Writing a dissertation and publications
  • Participation in regular events offered by the SecInt Doctoral College
  • Completion of an internship with one of our research partners
  • Presentation of research results and participation in scientific events 


Similar Positions