Vrije Universiteit, a highly ranked university, will start a multi disciplinary research project on 'Hybrid Explainable Workflows for Security and Threat Intelligence' and is looking for three PhD students; one focusing on formal reasoning about security and threat intelligence (this one) one on automated analysis of uncertainty and another one on experimental validation. Please check VU vacancy website for the other two PhD positions.
The PhD students at VU will work closely together with our colleagues at TU Delft University and Leiden University working on governance and public policy. The students will also work in close collaboration with Thales and TNO where part of the research will be carried out.Project: Security Threat Intelligence hybrid workflows
For security threat intelligence humans and artificial intelligence collaborate to obtain actionable intelligence. Their sources and methods often have significant uncertainties and biases. Experts are aware of such limitations but lack formal means to handle these uncertainties in their daily work. You will collectively work towards the high-level goals of building a ``metadata of uncertainty'' for threat intelligence (in both machine-readable and also human-interpretable forms) and validating it empirically. Intelligence agencies could then explicitly reason about the trade-off between accuracy, proportionality, privacy and cost-effectiveness of investigations. This contributes to using AI for better security and securing AI for a better society.Your duties
- To contribute towards solving a key scientific challenge in the area of security and intelligence
- To model a new (graph-based) representation that captures several types and operations of uncertainty that are intrinsic to the domain of threat intelligence, as well as the provenance of decisions made.
- To define and formalise the analysis of key properties that enable, among other, a sound reasoning about: i) alternative actions (what-if-analysis) under uncertain conditions, ii) assurance of proportionality of actions in threat intelligence scenarios
- To work part of a team of fellow researchers and students, share research ideas, results, and effectively communicate progress to produce top quality results
- To develop the necessary empirical protocols and measures and package them for broader impact (e.g., for study replications from other research fields or by industry and public administration partners)
- Writing scientific publications as the main driving force and as co-author, attending international conferences and workshops to present own work and maintain up-to date with latest research findings
- Support educational activities related to one's research field.