BayQS: Bavarian Competence Center for Quantum Security and Data Science

Logo des Bayerischen Kompetenzzentrum Quanten Security and Data Science
© BayQS

The Bavarian Competence Center for Quantum Security and Data Science (BayQS) is a merger of the three Fraunhofer Institutes AISEC, IIS and IKS with the Technical University of Munich, the Leibniz Supercomputing Centre (LRZ) and the University Hospital at Munich’s Ludwig-Maximilians-Universität (LMU). The center aims to address three important aspects of quantum computing, a discipline that is still in its early stages:

  • Cybersecurity
  • Reliability and robustness
  • Optimization

Although there is still a lot of research to be done in the area of hardware for quantum computing, the progress that has been made in software means that we have reached an ideal point to focus on developing secure, reliable and efficient quantum computing software.

Robust and reliable quantum computing

The research community is pinning its hopes on quantum computers being able to process data much more efficiently than their conventional counterparts. This will open up the potential for future quantum computing applications to solve problems that cannot yet be solved today. However, these capabilities can only be of real use if quantum computing results are reliable. In this context, quantum computing needs not only sheer computing power, but also robustness in order to be successful.

The Fraunhofer Institute for Cognitive Systems IKS is contributing its expertise in safety, robustness and reliability to two BayQS Center projects:

Quantum computing for verifying neural networks

In the project concerning QC-based certification of neural networks, Fraunhofer IKS is working with the TUM Data Analytics and Machine Learning Group on research into how quantum technologies can make autonomous networked systems safer. The aim is to verify complex AI methods, especially neural networks, using quantum computing.

In recent years, neural networks have been established in many sectors, including image recognition, speech processing and sensor data processing. However, a unique aspect of AI methods is that even the smallest changes in the input data can result in huge changes in the predictions. This means that large and complex neural networks cannot currently be used in safety-critical areas because they are not robust enough to deal with disturbances.

To change this, AI-based applications need to be verified and checked for compliance with certain specifications. However, verifying real applications poses a particular challenge because certification requires significant computational power. This is where quantum computers can be of use, as they have a far higher computing capacity than conventional computers. In its work with the BayQS Center, Fraunhofer IKS is therefore researching whether quantum computing can perform efficient certification of neural networks. The aim is not only to develop executable prototypes and algorithms, but also to test the methods on concrete application data.

It will be possible to use the results of this project to certify AI solutions more efficiently in the future – in applications such as autonomous driving, medicine or production.

Quantum computing and artificial intelligence for reliable medical diagnoses

Medical imaging data (MRI or CT scans, for example) plays a vital role in diagnosing and treating serious diseases. Because of this, artificial intelligence (AI) and machine learning methods – such as image analysis based on deep learning – are becoming an increasingly important part of medical diagnostics. However, the deep neural networks (DNNs) often used in these processes require a large amount of image data in order to make reliable conclusions. Depending on the situation, this training data may only be available in small quantities and can be expensive to obtain. It is also highly complex.

Not only that, but there are high stakes associated with AI-based systems in medical applications. Since an incorrect diagnosis can have serious consequences for the individual patient, the decision-making process in the AI system must be transparent and comprehensible. In addition, any uncertainty present in the diagnosis should be quantifiable.

Together with the University Hospital at Munich’s Ludwig-Maximilians-Universität (LMU), Fraunhofer IKS has set itself the goal of improving medical diagnoses through hybrid quantum computing-based machine learning models in a project that is focusing on highly reliable QC-based artificial intelligence for medical diagnostic tasks.

The advantage of a hybrid approach combining quantum technology and conventional methods is that it opens up the option of using an NISQ (noisy intermediate-scale quantum) computer. These computers are already available for industrial use.

Fraunhofer IKS is working on two approaches to improve medical diagnostics with the help of quantum computing:

  • Improved training through quantum convolutional neural networks (QCNNs)
    The aim of using QCNNs is to improve training with little data. In these networks, standard convolutional levels are replaced by quantum circuits. The MNIST dataset has already demonstrated that this approach improves training and increases accuracy even where smaller image data quantities are available. Fraunhofer IKS is transposing it to high-resolution image data in practical medical applications.
  • Reliable uncertainty determination through quantum Bayesian neural networks (BNNs)
    The advantage of BNNs is that they consistently rely on probability distribution rather than point estimation (which DNNs use). Cases involving complex tasks quickly become too much for BNNs to cope with as they can no longer be trained at that point. However, quantum computing-based BNNs make training possible even in the case of complicated tasks, ensuring reliable uncertainty determination when it comes to making diagnoses.

These quantum computing approaches could help achieve a breakthrough in the field of AI-based diagnostic processes. One of the long-term goals is to improve early and follow-up diagnoses of brain tumors – but every other machine learning application could also benefit from more efficient training through quantum computing, thanks to the time and costs saved. Combining quantum computing and artificial intelligence can be particularly beneficial in any safety-critical area that requires specific assessments of uncertainty to be reliable – mobility, production and medicine are some examples.