Concentrated Differential Privacy
arXiv:1603.01887v2491 citations
Originality Highly original
AI Analysis
This addresses the trade-off between privacy and utility for data analysts and researchers, representing a novel relaxation rather than an incremental improvement.
The paper tackles the problem of balancing privacy and accuracy in differential privacy by introducing Concentrated Differential Privacy, which achieves better accuracy than pure and (epsilon,delta) differential privacy while maintaining cumulative privacy loss over multiple computations.
We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without compromising on cumulative privacy loss over multiple computations.