Bernhard Berger

Bernhard J. Berger, Christina Plump, Rolf Drechsler

As AI solutions enter safety-critical products, the explainability and interpretability of solutions generated by AI products become increasingly important. In the long term, such explanations are the key to gaining users' acceptance of AI-based systems' decisions. We report on applying a model-driven-based optimisation to search for an interpretable and explainable policy that solves the game 2048. This paper describes a solution to the GECCO'24 Interpretable Control Competition using the open-source software EvoAl. We aimed to develop an approach for creating interpretable policies that are easy to adapt to new ideas.

Steffen Bartsch, Karsten Sohr, Michaela Bunke et al.

Mobile phones have developed into complex platforms with large numbers of installed applications and a wide range of sensitive data. Application security policies limit the permissions of each installed application. As applications may interact, restricting single applications may create a false sense of security for the end users while data may still leave the mobile phone through other applications. Instead, the information flow needs to be policed for the composite system of applications in a transparent and usable manner. In this paper, we propose to employ static analysis based on the software architecture and focused data flow analysis to scalably detect information flows between components. Specifically, we aim to reveal transitivity of trust problems in multi-component mobile platforms. We demonstrate the feasibility of our approach with Android applications, although the generalization of the analysis to similar composition-based architectures, such as Service-oriented Architecture, can also be explored in the future.