Departments

Our research fields in five departments

At the Institute for AI Safety and Security, we work in various research fields divided into five departments. Each department focuses on one specific area of AI, and thus on the specific requirements and needs of the target groups concerned. Together, we want to develop artificial intelligence and AI-based systems or solutions that are safe, secure, sufficiently assessable and highly relevant to practice.

AI Engineering - With engineers in view

Development processes, evaluation and test methods for AI-based components and systems in safety-critical applications; integration of results in decentralised DevOps environments (AI-in-the-loop) to increase the connectivity, resilience and cost-effectiveness of AI; research to improve the ability of humans and AI to interact (human-in-the-loop).

Algorithms & Hybrid Solutions - Getting everyone on board

Development of AI methods and technologies that are demonstrably safe in terms of safety and security and that embed themselves in distributed data and service ecosystems. Social, human and technological AI research and further development in synergy.

Safety-critical Data Infrastructures - More than encryption

Data and information quality as well as foundations for secure and distributed data infrastructures; methods and technologies of IT security and data encryption as well as privacy-preserving or privacy-enhancing technologies (PET). Prerequisites for safe and secure data exchange and robust AI applications in industry and research.

Execution Environments & Innovative Computing Methods - Distribute and integrate

Integration of innovative Artificial Intelligence in challenging systems - beyond classical thinking. Attack-proof and robust AI by securing the entire computing environment: mainframes, mobile devices, quantum computers.

Business Development and Strategy - Looking ahead and leading the way

Ongoing analysis of the research field and establishment of a network of AI science and industry. Coordination of trans- and interdisciplinary research on ELSA issues (ELSA = Ethical, Legal and Social Aspects) in the context of AI-based applications. Foundations for trustworthy AI, social acceptance and technology transfer.