Software doping analysis for human oversight

S Biewer, K Baum, S Sterz, H Hermanns… - Formal Methods in …, 2024 - Springer
This article introduces a framework that is meant to assist in mitigating societal risks that
software can pose. Concretely, this encompasses facets of software doping as well as …

Is your software on dope? Formal analysis of surreptitiously “enhanced” programs

PR D'Argenio, G Barthe, S Biewer, B Finkbeiner… - European Symposium …, 2017 - Springer
Usually, it is the software manufacturer who employs verification or testing to ensure that the
software embedded in a device meets its main objectives. However, these days we are …

[PDF][PDF] From Machine Ethics To Machine Explainability and Back.

K Baum, H Hermanns, T Speith - ISAIM, 2018 - academia.edu
We find ourselves surrounded by a rapidly increasing number of autonomous and semi-
autonomous systems. Two great challenges arise from this development: Machine Ethics …

Towards a framework combining machine ethics and machine explainability

K Baum, H Hermanns, T Speith - arXiv preprint arXiv:1901.00590, 2019 - arxiv.org
We find ourselves surrounded by a rapidly increasing number of autonomous and semi-
autonomous systems. Two grand challenges arise from this development: Machine Ethics …

Doping tests for cyber-physical systems

S Biewer, PR D'argenio, H Hermanns - ACM Transactions on Modeling …, 2021 - dl.acm.org
The software running in embedded or cyber-physical systems is typically of proprietary
nature, so users do not know precisely what the systems they own are (in) capable of doing …

Building bridges for better machines: from machine ethics to machine explainability and back

T Speith - 2023 - publikationen.sulb.uni-saarland.de
Be it nursing robots in Japan, self-driving buses in Germany or automated hiring systems in
the USA, complex artificial computing systems have become an indispensable part of our …

Expanding explainability: from explainable artificial intelligence to explainable hardware

T Speith, J Speith, S Becker, Y Zou, A Biega… - arXiv preprint arXiv …, 2023 - arxiv.org
The increasing opaqueness of AI and its growing influence on our digital society highlight
the necessity for AI-based systems that are trustworthy, accountable, and fair. Previous …

A micro and macro perspective on trustworthiness: theoretical underpinnings of the Trustworthiness Assessment Model (TrAM)

N Schlicker, K Baum, A Uhde, S Sterz, MC Hirsch… - 2022 - osf.io
Designing trustworthy systems and enabling external parties to accurately assess the
trustworthiness of these systems are crucial objectives. Only if trustors assess system …

Software doping–Theory and detection

S Biewer - 2023 - publikationen.sulb.uni-saarland.de
Software is doped if it contains a hidden functionality that is intentionally included by the
manufacturer and is not in the interest of the user or society. This thesis complements this …

[PDF][PDF] Faculty of Philosophy Department of Philosophy

T Speith - 2023 - core.ac.uk
Be it nursing robots in Japan, self-driving buses in Germany or automated hiring systems in
the USA, complex artificial computing systems have become an indispensable part of our …