- Privacy-preserving AI – Why do we need it? - May 29, 2020.
Various data privacy threats can result from the usual process of building and constructing data and AI-based systems. Avoiding these challenges can be supported by utilizing state-of-the-art technologies in the domain of privacy-preserving AI.
- PySyft and the Emergence of Private Deep Learning - Jun 27, 2019.
PySyft is an open-source framework that enables secured, private computations in deep learning, by combining federated learning and differential privacy in a single programming model integrated into different deep learning frameworks such as PyTorch, Keras or TensorFlow.
- The 7 Myths of Data Anonymisation - Mar 12, 2019.
Anonymisation has always been rather seen as a necessary evil instead of a helpful tool. That’s why plenty of myths have arisen around that technology over the years.
- What is it like to be a machine learning engineer in 2018? - Jun 21, 2018.
A personal account as to why 2018 is going to be a fun year for machine learning engineers.
- How to build analytic products in an age of data privacy - May 17, 2018.
Privacy-preserving analytics is not only possible, but with GDPR about to come online, it will become necessary to incorporate privacy in your data products.
- Privacy Software Analysis Project - Jul 17, 2017.
Experienced Java developer with statistics and/or data privacy background to review and analyze one or more open source projects in the data privacy space and write reports on the functionality of those projects.
- A Simpler Explanation of Differential Privacy - Nov 6, 2015.
Privacy concerns in data mining have been raised from time to time, could differential privacy be a solution? Differential privacy was devised to facilitate secure analysis over sensitive data, learn how it can be used to improve the model fitting process.
Pages: 1 2 3
- Differential Privacy: How to make Privacy and Data Mining Compatible - Jan 9, 2015.
Can privacy coexist with machine learning and data mining? Differential privacy allows the learning of general characteristics of populations while guaranteeing the privacy of individual records.