We are looking for a motivated PhD candidate that wants to develop new visual analtyics methods for the exploration, analysis, and explainability of multimodal evidence data, supported by AI.
Law enforcement is faced with huge amounts of data from online platforms, digital marketplaces, or communication services. Finding evidence in such large collections of text, images, and other data and bringing it to court is a time-consuming process. Artificial Intelligence tools are a promising way to make this more efficient and effective. But currently no clear legal regulations for AI tools are in place. In AI4Intelligence we let AI tool development, the use of the tools by investigators, and legal regulations go hand-in-hand so investigations lead to trustworthy evidence that is admissible in court.
The candidate is expected to research and develop visual analytics methods to increase model transparency and provide explanations to ensure trustworthy evidence from multimodal data. He/she develops visual analytics tools & techniques:
- To explain AI model predictions for both the data scientist and non-technical stakeholders; and
- For multimodal data exploration, hypothesis generation and testing, and link discovery, using a (hyper)graph/network analysis approach.
The project will be developed within the Visualization cluster under the supervision of Dr.ir. Stef van den Elzen and Prof.dr. Anna Vilanova. This position is part of the NWO KIC AI4Intelligence project with collaborators from university (University of Amsterdam, Utrecht University, VU Amsterdam, University of Applied Sciences Leiden, University of Applied Sciences The Hague), government (Netherlands National Police, Netherlands Forensic Institute), and industry (Miscrosoft, TNO, Sustainable Rescue Foundation, SynerScope, CFLW Cyber Strategies, DuckDuck-Goose, ZiuZ Forensics BV, BG.legal). The project brings together scientific scholars from computer science (UvA,UU,TU/e), management (UU), and law (VU) which are an essential combination to address the challenges posed. Within computer science three related, but complementary perspectives on data, its analysis, and exploration are present in the consortium. Data-driven machine learning (UvA), knowledge driven AI (UU) and visual analytics (TU/e). The researchers from the different disciplines will all work on the two use cases bringing in their own expertise, continuously building upon the achievements of the others and influencing the research of others.
The visualization cluster (https://research.tue.nl/en/organisations/visualization-3) at TU/e has a strong track record in visualization and visual analytics for ML models and high-dimensional data. It has generated several award winning contributions at major visualization conferences (IEEE VIS, IEEE InfoVis, IEEE VAST, EuroVis); several successful start-up companies (MagnaView - now UiPath and SynerScope); and a number of techniques that are used on a large scale world-wide.