This short whitepaper aims to create the beginnings of a framework for best practices standards by focusing on specific privacy and security vulnerabilities within ML systems. At present, we view these vulnerabilities as warning signs—either of a future in which the benefits of ML are not fully embraced, or a future in which ML’s liabilities are insufficiently protected.
The Curse of Dimensionality: De-identification Challenges in the Sharing of Highly Dimensional Datasets
De-identifying search query data under GDPR is fraught with risk as high-dimensional behavioural datasets remain vulnerable to re-identification despite technical […]