R2: Prosilience and Long-term Robustness through Human-centered Design

AI technologies can be supported by mathematical guarantees – yet, these hold for well-defined settings of the introduction phase and for ‘technical’ objectives rather than human-centered ones (e.g., fairness of ITS for users with different ethnicity or gender). Complex ITS violate the conditions of such mathematical guarantees during their life-cycle, since the behavior of human partners, social context, and technical environment can be subject to (unexpected) variations, and the long-term societal and technological impact of ITS can hardly be overseen. Within SAIL, we aim for prosilience – proactive actions to guarantee resilience over time – as a fundamental design principle for robust behavior in unexpected situations with respect to diverse (technology-centered and human-centered) requirements. We address three overarching research questions:

  • How do humans perceive restrictions and errors of ITS? How can limitations and uncertainties of ITS be modeled and communicated?
  • How can emerging risks of ITS be identified, involving technological malfunctioning and possible harm on individual humans or social relations? What are self-stabilizing strategies within an interactive human-centered design to counter such long-term deteriorating effects?
  • How can life-long flexibility of ITS in evolving environments be realized to integrate changing preferences? How can specialized ITS be safely deprecated? How to deal with an update against established interaction patterns?

Explore R2 Prosilience & Robustness Projects

Application area: Industry

Justice and Fairness Perceptions in Automated Decision-Making

by Paul Hellwig
Automated Decision-Making Fairness Procedural Justice Bielefeld University
R2 Prosilience & Robustness

Adopting and Adapting Machine Learning in the Digital Humanities

by Sophie Spliethoff
Digital Humanities Hate Speech Bielefeld University
R2 Prosilience & Robustness

Sustainable use of AI-based electronic noses in the life science field in changing environments

by Julius Wörner
TH OWL
Application area: Industry

Embedded code embeddings

by Sebastian Sierra
Neural Networks Paderborn University
R2 Prosilience & Robustness

Modelling and Controlling Dynamical Systems

by Thorben Markmann
Robustness Bielefeld University
R2 Prosilience & Robustness

Robust Training based on Semantic Adversarials

by Julian Knaup
TH OWL
R2 Prosilience & Robustness

Solidarity with Migrants/Women in German Political Debates: An Analysis via Large Language Models

by Aida Kostikova
LLMs Bielefeld University
R2 Prosilience & Robustness

Reinforcement learning on continuous and deterministic systems

by Hans Harder
Reinforcement Learning Paderborn University
R2 Prosilience & Robustness

Processes of Social Inclusion/Exclusion in Hybrid Teams

by Alexandra Florea
Data Literacy Paderborn University
R2 Prosilience & Robustness

Robust deep active learning for data streams

by Eiram Mahera Scheikh
Active Learning HSBI
R2 Prosilience & Robustness

Social Exclusion in Human-Technology Interaction

by Clarissa Sabrina Arlinghaus
Bielefeld University
R2 Prosilience & Robustness

Prediction of driving dynamics in the context of interactive driving simulation

by Keno Pape
Intelligent Systems Prediction Self-aware AI Paderborn University