Bitfount

Privacy-Enhancing Technologies (PETs)

Trusted Execution Environments | Privacy-Enhancing Technologies PETs

Trusted Execution Environments are one mechanism for enabling multiple parties to collaboratively do computation. The security depends on the computation running in an environment that all the parties trust.

Privacy-Enhancing Technologies (PETs)

6 min read

Secure Multiparty Computation | Multiparty Computation | Privacy-Enhancing Technologies PETs

Secure multiparty computation (MPC / SMPC) is a cryptographic protocol that distributes a computation across multiple parties where no individual party can see the other parties’ data.

Privacy-Enhancing Technologies (PETs)

6 min read

Machine Learning Model Evaluation | Federated Machine Learning | Privacy-Enhancing Technologies PETs

Federated ML model evaluation allows you to send a trained ML model you wish to evaluate to the data, rather than requiring the data to be centralised first.

Privacy-Enhancing Technologies (PETs)

6 min read

Synthetic Data | Synthetic Data Generation | Privacy-Enhancing Technologies PETs

Synthetic datasets are becoming increasingly popular for training artificial intelligence models in place of the original raw datasets from which they are generated. It is a computer-generated dataset sufficiently similar to an original base dataset.

Privacy-Enhancing Technologies (PETs)

6 min read

Federated Machine Learning | Privacy-Enhancing Technologies PETs

Federated Learning (FL) is simply a Machine Learning (ML) setting where many clients collaboratively train a model under the orchestration of a central server while keeping the training data decentralised.

Privacy-Enhancing Technologies (PETs)

6 min read

Privacy Enhancing Technologies (PETs) | What are PETs | Examples

PETs are a set of technologies which mitigate the risk to the individual of data privacy abuse.

Privacy-Enhancing Technologies (PETs)

6 min read

Differential Privacy | Privacy-Enhancing Technologies PETs

Differential Privacy addresses the paradox of learning nothing about an individual while learning useful information about a population. Differentially private techniques protect the privacy of individual data subjects by adding random noise when producing statistics.

Privacy-Enhancing Technologies (PETs)

6 min read

Tokenization | Sprint Tokenization | Data tokenization | Privacy-Enhancing Technologies PETs

Tokenization is the process through which one “substitutes a sensitive identifier (e.g., a unique ID number or other PII) with a non-sensitive equivalent (i.e., a ‘token’) that has no extrinsic or exploitable meaning or value”

Privacy-Enhancing Technologies (PETs)

6 min read

Homomorphic Encryption Guide | Fully Homomorphic Encryption | Privacy-Enhancing Technologies PETs

Homomorphic Encryption methods are encryption schemes which allow mathematical operations to be performed on the underlying data whilst keeping the data in the encrypted space.

Trusted Execution Environments | Privacy-Enhancing Technologies PETs

Secure Multiparty Computation | Multiparty Computation | Privacy-Enhancing Technologies PETs

Machine Learning Model Evaluation | Federated Machine Learning | Privacy-Enhancing Technologies PETs

Synthetic Data | Synthetic Data Generation | Privacy-Enhancing Technologies PETs

Federated Machine Learning | Privacy-Enhancing Technologies PETs

Privacy Enhancing Technologies (PETs) | What are PETs | Examples

Differential Privacy | Privacy-Enhancing Technologies PETs

Tokenization | Sprint Tokenization | Data tokenization | Privacy-Enhancing Technologies PETs

Homomorphic Encryption Guide | Fully Homomorphic Encryption | Privacy-Enhancing Technologies PETs

Get started for free

Product

Solutions

Resources

Company