The study focuses on the intersection of cybersecurity and AI reproducibility. It introduces a new framework for evaluating AI platforms’ reproducibility from a cybersecurity perspective. Five popular AI platforms were…
Continue readingThe paper presents an investigation into K-norm mechanisms used in differentially private computations. It discusses how these mechanisms can yield more accurate additive noise by using a statistic-specific norm. The…
Continue readingThis study aims to improve the performance of prefix-tree-based algorithms for differentially private heavy hitter detection. To enhance this, an adaptive hyperparameter tuning algorithm is introduced. It helps to increase…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
