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.

DownloadDownload

How can artificial intelligence be optimised for specific systems? How do we secure devices that use AI? How do we integrate AI into existing processes and devices? Our scientists in the Execution Environments and Innovative Computing Methods department are working on these and similar questions.

In order to embed artificial intelligence into our technology in a secure and uncompromising way, the entire system on which the AI is executed must be considered. To this end, the department is working on securing AI models at various levels close to the hardware. We are investigating the suitability of quantum computers for AI applications and optimising AI for high-performance computers and distributed systems. The Gaia-X 4 AGEDA project explores virtual platforms for the permanent integration of AI software modules in vehicle technology.

We are also active in highly specialised application areas such as automated vehicles and various aerospace applications that require exceptional levels of reliability. In distributed system environments such as cloud services or Gaia-X, it is important that AI methods are provided in a device-independent manner. This is the only way to ensure that AI can be executed safely and efficiently. Our application-independent architecture makes it easy to transfer the methods to new tasks.

Quantum computing and other innovative computing approaches are an important aspect of the design of future generations of AI. We analyse the possibilities and consequences of new computing methods for artificial intelligence. Specific questions include how to implement secure and comprehensible AI on quantum computers, what opportunities the quantum world offers for the development of new methods beyond the improvement of classical algorithms, how new approaches can be embedded in existing classical processes and structures, and what attack scenarios on our IT infrastructures and defence mechanisms will look like in the future.

Projects of the Execution Environments & Innovative Computing Methods Department

Hidden order among disorder

DataMat

The Helmholtz Young Investigator Group DataMat wants to turn fundamental insights about new states of matter into materials with properties that were thought to be impossible before. The group pursues a “hidden” order amongst disorder, that is, systems that seem to be random but that are homogeneous like crystals at large distances. Such systems look the same in every direction like a liquid; globally, however, they suppress density fluctuations like a crystal.

How to use Quantum computers?

ELEVATE

Enabling DLR-Institutes to apply quantum computing to the real world: The development of modern quantum computers is just now reaching a stage where the first applications will also offer practical quantum advantages in comparison to classical programmes. To support DLR's quantum initiative, the ELEVATE project provides a network to support scientists from all DLR institutes in the feasibility analysis of quantum computer projects.

Tensor networks for quantum-classical applications

QuTeNet

The capabilities of quantum computers promise a paradigm shift for extremely computationally intensive applications such as optimisation problems, the simulation of quantum systems and artificial intelligence (AI). A particularly promising approach in the field of AI is the evaluation of quantum states by quantum AIs, as there is no loss of information when switching to a classical system through a measurement.

Evaluating Quantum AI

Quant²AI

Quantum computers are expected to offer immense advantages over classical computers, especially for resource-intensive applications such as artificial intelligence. The Institute for AI Safety and Security is investigating whether these hopes can be realised in the project Quantification of Quantum Advantages for Artificial Intelligence from a heuristic point of view.

Artificial Intelligence for Everyone

ReBAR

The increasing spread of machine learning opens up enormous development potential in a wide variety of application areas - such as engineering, transport and medicine. In the meantime, a wide range of methods is available with a confusing variety of implementations. The contribution of our institute includes the two focal points of architecture definition and verification & visualisation.

Contact

Dr. Hans-Martin Rieser

Research Associate / Interim Head of Department
German Aerospace Center (DLR)
Institute for AI Safety and Security
Execution Environments & Innovative Computing Methods
Wilhelm-Runge-Straße 10, 89081 Ulm

Karoline Bischof

Consultant Public Relations
German Aerospace Center (DLR)
Institute for AI Safety and Security
Business Development and Strategy
Rathausallee 12, 53757 Sankt Augustin