Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects
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.
Code (0)
등록된 구현이 없습니다.
Tasks
EthicsFairnessSimilar Papers 제목 키워드 기반
Resolving Ethics Trade-offs in Implementing Responsible AI
While the operationalisation of high-level AI ethics principles into practical AI/ML systems has made progress, there is still a theory-practice gap in managing tensions between the underlying AI ethics aspects. We cover…
EthicsAI Ethics Principles in Practice: Perspectives of Designers and Developers
As consensus across the various published AI ethics principles is approached, a gap remains between high-level principles and practical techniques that can be readily adopted to design and develop responsible AI systems.…
EthicsFairnessResponsible AI: The Good, The Bad, The AI
The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly atte…
Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI
Federated Learning (FL) enables collaborative machine learning while preserving data privacy but struggles to balance privacy preservation (PP) and fairness. Techniques like Differential Privacy (DP), Homomorphic Encrypt…
BenchmarkingFairnessFederated LearningA Convex Loss Function for Set Prediction with Optimal Trade-offs Between Size and Conditional Coverage
We consider supervised learning problems in which set predictions provide explicit uncertainty estimates. Using Choquet integrals (a.k.a. Lov{á}sz extensions), we propose a convex loss function for nondecreasing subset-v…
Binary Classification