Invited Speakers
Key Note
Exploring the Landscape of Federated Learning Systems and Applications: Advantages, Challenges, and Security Concerns
Prof. Dr.-Ing. Alexandra Dmitrienko
Chair of Secure Software Systems, University of Würzburg
alexandra.dmitrienko(at)uni-wuerzburg.de
Abstract of the Talk
Machine Learning (ML) methods have reached a level of maturity where they are being widely deployed across various domains, aiding users in classification and decision-making tasks. In this presentation, we will showcase the numerous advantages ML offers for applications dedicated to detecting security threats on mobile platforms. However, it is important to address the security and privacy concerns that arise when utilizing ML methods. One particular focus of our talk will be on Federated Learning (FL), which is a distributed form of ML that enhances privacy preservation during the training of ML models. We will conduct a comprehensive evaluation of the security and privacy risks associated with FL, delving into the intricacies of targeted and untargeted poisoning attacks, as well as the countermeasures employed to mitigate these threats. Our discussion will highlight the ongoing challenges in this field, such as the ability to differentiate between poisoned models and benign but uncommon models, particularly those trained on datasets with different data distributions. We will also address the issue of adaptive attackers who, once aware of the detection method, can add an additional training loss to minimize any changes in the detection metric, effectively evading detection. To stimulate further dialogue and exploration, we will outline promising research directions and open avenues for future research work.
Keywords: Machine Learning (ML), Federated Learning Systems
Invited Talk: Advancing AI in Healthcare: Empowering Radiology through Image-Based Approaches
Prof. Dr. Christian Ledig
Chair of Explainable Machine Learning, University of Bamberg
christian.ledig(at)uni-bamberg.de
Abstract of the Talk
In recent years, the integration of artificial intelligence (AI) in healthcare has shown tremendous promise, particularly in image-based applications such as radiology. This invited talk is concerned with the continuously increasing need to responsibly integrate AI technology into healthcare applications, while emphasizing its transformative potential. The healthcare industry is faced with the challenge of processing and analysing and ever-growing volume of imaging data. AI-driven image analysis can offer a possible solution by enabling clinical experts to more efficiently and more accurately interpret medical images. However, the adoption of AI in the healthcare sector comes with significant technical challenges, regulatory obligations as well as societal implications. The talk will highlight opportunities and difficulties that must be considered when implementing AI in clinical applications, a particular benefit being the potential to improve access to consistent, more accurate and more objective diagnoses.
Keywords: AI-driven image analysis
Invited Talk: Detecting hidden innovative networks in hacker communities
Dr. Joachim Klerx
AIT Austrian Institute of Technology GmbH, Foresight & Policy Development Department
Abstract of the Talk
Innovation networks have always been in the core of human wealth, because of their contribution to increased economic efficiency. Hacker communities in particular have been proven to be the fastest and most successful innovation network. This paper presents a method to extend the concept of innovation networks, by elements of innovation from the digital ecosystem and more specifically the crypto ecosystem and to use artificial intelligence to discover the specific hidden part of the innovation networks. By using specific sources from the internet about community communication on platforms in surface web, deep web and dark nets, in addition to publication analytics and patent analytics, the hidden part of the innovation networks will be made visible and accessible to further analytics. Understanding the methods from hacker communities is essential for the digital transformation in public services, universities and other organizations.