Masterarbeit
Enhancing a Security Assessment Tool with Semantic Knowledge Graphs and Interactive Conversational Interfaces
Completion
2025/11
Research Area
Students
Utkarsh Yadav
Advisers
Verena Traubinger M.Sc.
Dr.-Ing. Sebastian Heil
Description
Chatbots are increasingly deployed as primary touchpoints for users across various digital platforms, serving roles that span information delivery, assistance, and decision support. In the specific field of cyber security, rapid evolution of cyber threats demand that conversational systems have to be capable of deep semantic reasoning and dynamic user interaction to address context-sensitive security challenges. One technical solution for this are knowledge graphs, while the semantic reasoning and its complex relationships also have to be presented in a well understandable way to the users. Based on the previously conducted Planspiel, a conversational user interface for security threat analysis is enhanced with knowledge graphs and interactive interfaces to create a better user experience for its users.
This thesis researches on the development of an adaptive conversational interface that translates complex semantic content from a knowledge graph implementation into a personalized and cognitively supportive user experience. The approach centers on a progressive UX framework integrating micro-tooltips, contextual disclosure, semantic chat history navigation, and AI-generated task cards to enhance comprehension and task continuity. The different interfaces are designed to reflect underlying KG structures while adjusting to user roles through a mode selector mechanism. The evaluation involves role-specific scenarios tested across cybersecurity professionals, learners, and UX experts, with feedback captured through both usability scores and qualitative analysis.
The objective of this thesis is the creation of a solution or the combination of existing approaches to solve the above described problem of creating an interactive user interfaces for representing contextual information from a knowledge graph about security threat assessment. This includes the analysis of the state of the art of current graphical and conversational interface design conventions, visual or textual representations of contextual information from knowledge graphs, and other relevant literature. From this analysis, a possible solution should be conceptualized and demonstrated by creating a prototypical implementation of an adaptive user interface for an existing conversational security threat assessment tool enhanced with a knowledge graph from the Planspiel module, as well as a suitable evaluation based on qualitative and quantitative user testing and its compliance with requirements which were extracted through the literature research.
