Artificial intelligence can be encountered in many places; it is a key technology that is becoming increasingly important in the course of advancing digitalisation. The aspect of AI security - both in the sense of protection against external attacks (security) and flawlessness or reliability of operation (safety) - is accordingly gaining in relevance. Only a deeper examination of the security of AI-based technologies and applications can enable their comprehensive use for the benefit of the economy and society.
At the Institute for AI Security, we research and develop AI-related methods, processes, algorithms, technologies and system or execution environments. Our focus is on ensuring operational and attack security for AI-based solutions in ambitious application classes. We therefore primarily examine technology fields which are particularly security-critical. This applies to applications in aerospace, ground-based transport, the field of energy and many aspects of our infrastructure which are relevant to everyday life. The smarter our environment becomes, the more relevant AI security becomes. Last but not least, it also involves the organisation, storage and exchange of sensitive data in increasing quantities of distributed data infrastructures, i.e. questions of data sovereignty, transparency and shared use - and, consequently, the foundations of a networked Industry 4.0 and new digital services.
Our research fields at a glance:
DLR offers optimal framework conditions
DLR's research and development activities – which are shaped by aeronautics, space travel, energy and transport – and the associated research infrastructures provide an optimal framework for inter- and transdisciplinary research. As an example, our researchers can access extensive data sets from DLR's large-scale research facilities in order to analyse them using AI or to utilise them in the construction of AI systems.
The work of the AI Institute is cross-sectoral and therefore actively contributes towards a unique constellation at DLR. Broadly diversified expertise from various scientific disciplines and in-depth application knowledge are merged together with fundamental AI research. In this way, we can ensure a subject-specific further development of the topic of AI and, at the same time, a high level of practical and application relevance. Our research and development activities are flanked by AI-related networking activities on the topics of ethics, law and society.
At the Institute for AI Security, we want to enable reliable AI through fundamental research and with new methods and to thereby overcome barriers to the success of new technologies. Specifically, we aim to make new contributions towards the responsible introduction of AI in practical applications with high security requirements.