The Fundamental Limits of Least-Privilege Learning
This addresses the problem of privacy and utility in machine learning for researchers and practitioners, showing that achieving perfect least-privilege learning is fundamentally limited, making it a foundational but incremental theoretical contribution.
The paper formalizes the least-privilege principle in machine learning and proves a fundamental trade-off: it is impossible to learn representations with high utility for a task while preventing inference of any non-task attributes, which holds under realistic assumptions and is empirically validated across various techniques and datasets.
The promise of least-privilege learning -- to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this task -- is highly appealing. However, so far this concept has only been stated informally. It thus remains an open question whether and how we can achieve this goal. In this work, we provide the first formalisation of the least-privilege principle for machine learning and characterise its feasibility. We prove that there is a fundamental trade-off between a representation's utility for a given task and its leakage beyond the intended task: it is not possible to learn representations that have high utility for the intended task but, at the same time prevent inference of any attribute other than the task label itself. This trade-off holds under realistic assumptions on the data distribution and regardless of the technique used to learn the feature mappings that produce these representations. We empirically validate this result for a wide range of learning techniques, model architectures, and datasets.