I've been working in IT for the past 8 years. My journey began in web development, focusing on frontend technologies like JavaScript, and SASS. Along the way, I familiarized myself with PHP frameworks, particularly Laravel and TYPO3. During my bachelor's studies, I had the chance to work for two companies as a web developer and picked up skills in Clojure and Ruby. My interest in deeper aspects of IT prompted me to study media informatics. Here, I explored various topics like VR, games development, foundational programming and software engineering concepts. I worked on diverse projects, including ones that integrated AI for music. This experience had me working with Python, C, C#, Java, and JS. I then wrote my bachelor's thesis on an AI-related topic in collaboration with Data42. Motivated to learn further, I pursued a master's in computer science, emphasizing data science. This course also exposed me to software security as an additional elective subject and also into research methods. Later, I initiated a research project on responsible AI named VERIFAI, which I expanded upon in my master's thesis. Looking ahead, I plan to delve deeper into this subject for my doctoral research. Outside of research, I enjoy my role as a Teaching Assistant for Data Science Practice at the university, where I help students with hands-on experience and share my enthusiasm for the subject.
An evaluation of the responsibility of generative AI models presents unique challenges that require holistic and practical solutions. This paper introduces an enhanced version of the VERIFAI framework, which extends beyond classification models to assess generative language models as well… Read More »Towards Responsibility Evaluation of Generative Language Models
Our research endeavors to advance the concept of responsible artificial intelligence (AI), a topic of increasing importance within EU policy discussions. The EU has recently issued several publications emphasizing the necessity of trust in AI, underscoring the dual nature of… Read More »Responsible Artificial Intelligence: A Structured Literature Review
The growing integration of artificial intelligence (AI) in diverse sectors underscores the need for comprehensive and standardized approaches to ensure AI responsibility. However, the absence of a holistic framework to evaluate the fairness, privacy-preserving, secure, explainable, and human-centered facets of… Read More »Bridging the Gap between Theory and Practice: Towards Responsible AI Evaluation
This work represents the first step towards a unified framework for evaluating an AI system’s responsibility by building a prototype application.The python based web-application uses several libraries for testing the fairness, robustness, privacy, and explainability of a machine-learning model as… Read More »VERIFAI – A Step Towards Evaluating the Responsibility of AI-Systems