Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects

Abstract

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML systems.

References in corpus (9)

• Artificial Intelligence: the global landscape of ethics guidelines
• Federated Learning: Challenges, Methods, and Future Directions
• Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making
• Differentially Private Model Publishing for Deep Learning
• Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
• Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks
• A Review of Adversarial Attack and Defense for Classification Methods
• AI Ethics Principles in Practice: Perspectives of Designers and Developers
• Avoiding Disparity Amplification under Different Worldviews

Cited by in corpus (4)

• Towards a Privacy and Security-Aware Framework for Ethical AI: Guiding the Development and Assessment of AI Systems
• Resolving Ethics Trade-offs in Implementing Responsible AI
• Extreme Value Modelling of Feature Residuals for Anomaly Detection in Dynamic Graphs
• Predicting Graph Structure via Adapted Flux Balance Analysis