Institute for AI Safety and Security

At the Institute for AI Safety and Security, we research and develop AI-related methods, processes, algorithms, technologies and execution or system environments.

News from our institute

Loading
The Institute for AI Security introduces itself
At the Institute for AI Safety and Security, we research and develop AI-related methods, processes, algorithms, technologies and execution and system environments. We contribute to ensuring operational and attack security for AI-based solutions in ambitious application classes.

The Institute for AI Security introduces itself

Your consent to the storage of data ('cookies') is required for the playback of this video on Quickchannel.com. You can view and change your current data storage settings at any time under privacy.

The Institute for AI Security introduces itself
At the Institute for AI Safety and Security, we research and develop AI-related methods, processes, algorithms, technologies and execution and system environments. We contribute to ensuring operational and attack security for AI-based solutions in ambitious application classes.

Our research fields in five departments

AI Engineering

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

Algorithms & Hybrid Solutions

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

Data and information quality and the foundations for secure decentralized data infrastructures; methods and technologies of IT security and data encryption as well as privacy enhancing technologies (PET). Requirements for secure data exchange and robust AI applications in industry and research.

Execution Environments & Innovative Computing Methods

Research and development on reliable execution environments (software and hardware) and innovative computing approaches, in particular quantum computing. Attack-proof and robust AI by securing the entire execution system.

Business Development & Strategy

Continuous analysis of the research field and networking of AI science and industry. Coordination of inter-/transdisciplinary research on ELSA topics (ELSA = Ethical, Legal and Social Aspects) in the context of AI-based applications. Foundations for trustworthy AI, social acceptance and technology transfer.