by Markus Hittmeir, Andreas Ekelhart and Rudolf Mayer (SBA Research)

The generation of synthetic data is widely considered to be an effective way of ensuring privacy and reducing the risk of disclosing sensitive information in micro-data. We analysed these risks and the utility of synthetic data for machine learning tasks. Our results demonstrate the suitability of this approach for privacy-preserving data publishing.

by Andrea Fontanari and Kees Oosterlee (CWI)

The increasing use of drones is likely to result in growing demand for insurance policies to hedge against damage to the drones themselves or to third parties. The current lack of accident data, however, makes it difficult for insurance companies to develop models. We provide a simple yet flexible model using an archetype of Bayesian neural networks, known as Bayesian generalised linear models, to predict the risk of drone accidents and the claim size.

by Florian Skopik, Markus Wurzenberger, and Max Landauer (AIT Austrian Institute of Technology)

Most current security solutions are tailored to protect against a narrow set of security threats and can only be applied to a specific application domain. However, even very different domains share commonalities, indicating that a generally applicable solution, to achieve advanced protection, should be possible. In fact, enterprise IT, facility management, smart manufacturing, energy grids, industrial IoT, fintech, and other domains, operate interconnected systems, which follow predefined processes and are employed according to specific usage policies. The events generated by the systems governed by these processes are usually recorded for maintenance, accountability, or auditing purposes. Such records contain valuable information that can be leveraged to detect any inconsistencies or deviations in the processes, and indicate anomalies potentially caused by attacks, misconfigurations or component failures. However, syntax, semantics, frequency, information entropy and level of detail of these data records vary dramatically and there is no uniform solution yet that understands all the different dialects and is able to perform reliable anomaly detection on top of these data records.

by Michaël Tits, Mohamed Boukhebouze and Christophe Ponsard (CETIC)

Recent advances in deep neural networks have enabled great improvements in image restoration, a long-standing problem in image processing. Our research centre has experimented with cutting edge algorithms to address denoising, moire removal, colourisation and super resolution, to restore key images representing the photographic heritage of some of Belgium’s top athletes.

by Simon Tjoa (St. Pölten UAS, Austria), Christina Buttinger (Austrian Armed Forces), Katharina Holzinger (Austrian Armed Forces) and Peter Kieseberg (St. Pölten UAS, Austria)

Securing complex systems is an important challenge, especially in critical systems. Artificial intelligence (AI), which is increasingly used in critical domains such as medical diagnosis, requires special treatment owing to the difficulties associated with explaining AI decisions.  Currently, to perform an intensive security evaluation of systems that rely on AI, testers need to resort to black-box (penetration) testing. 

by Erwin Kristen, Reinhard Kloibhofer (AIT Austrian Institute of Technology, Vienna) and Vicente Hernández Díaz (Universidad Politécnica de Madrid)

The European agricultural sector is transforming from traditional, human labour-intensive work to data-oriented digital agriculture that has great potential for semi- or fully autonomous operation. This digital transformation offers many advantages, such as more precise fact-based decision making, optimised use of resources and big changes in organisation – but it also requires improved cyber-security and privacy data protection. 

by Thomas Lorünser (AIT), Niki Dürk (X-Net), Stephan Puxkandl (Ebner)

The FlexProd research project aims to develop a platform to improve the efficiency and speed of cross-company order allocation and processing in the manufacturing industry. The platform will help make production more flexible, facilitating cooperation between manufacturers and customers to enable a more agile and efficient manufacturing industry.

by Daniele Spoladore, Elena Pessot and Marco Sacco (STIIMA-CNR)

The HEALPS 2 project is using digital solutions and stakeholder engagement to unlock the potential of health tourism in the alpine regions.